
## The following packages will be needed for the analysis

import pandas as pd
import numpy as np
from sklearn import tree
from sklearn.tree import plot_tree

import seaborn as sns
import matplotlib.pyplot as plt
pd.set_option('display.max_columns', None)

sns.set_style("whitegrid")

from matplotlib import rcParams
rcParams['figure.figsize'] = 15, 5
from sklearn.model_selection import train_test_split #for train and test split
from imblearn.over_sampling import SMOTE


import warnings
warnings.filterwarnings("ignore")
import nltk
import re
import string
import nltk
nltk.download('stopwords')

from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
stopwords = stopwords.words('english')
from imblearn.over_sampling import SMOTE
from matplotlib import rcParams
rcParams['figure.figsize'] = 15, 5
from sklearn.model_selection import train_test_split #for train and test split
from sklearn.model_selection import ParameterGrid, GridSearchCV
from sklearn.metrics import make_scorer, accuracy_score, classification_report

[nltk_data] Downloading package stopwords to
[nltk_data]     C:\Users\fahad\AppData\Roaming\nltk_data...
[nltk_data]   Package stopwords is already up-to-date!


df = pd.read_csv("Navigation_Dataset.csv")
df.head()


## Discard values of each feature that are 2x standard deviation away from the mean values
for feature in df.select_dtypes(include=['int16', 'int32', 'int64', 'float16', 'float32', 'float64']):
    df = df[np.abs(df[feature]-df[feature].mean()) <= (2*df[feature].std())]


df1=df['main_task'].str.split('/', expand=True)[:50]
df1


df1=df['urls'].str.split(',', expand=True)[:50]


##df = pd.read_csv("/dbfs/FileStore/shared_uploads/fa3015@att.com/Navigation_Dataset.csv")
##df.head()

df2=df[df.Searches==1]
df2


#df.loc[['Support']]
df1=df[df['Survey_Category']== 'Account Management']
df1=df1.set_index('Survey_Category')


df['Search']=["Didn't use search" if x == 0.0 else 'Used Search' for x in df['Searches']]
df1 = df[df['Searches']== 0.0]


fig,axs=plt.subplots(ncols=2)
fig.set_size_inches(15,5)
sns.histplot(binwidth=0.5, x='Survey_Category', hue = 'TA', data=df1[df1['Survey_Category']== 'Support'], stat="density", multiple="dodge", shrink=.8, ax=axs[0])
sns.histplot(binwidth=0.5, x='Survey_Category', hue = 'Navigation_Difficulties', data=df1[df1['Survey_Category']== 'Support'].sort_values(by = "Navigation_Difficulties"), stat="density", multiple="dodge", shrink=.8, ax=axs[1])

plt.grid(which='minor', linestyle=':', linewidth='0.5', color='black')

axs[0].set_title('Figure 1: TA when searches were not used')
axs[1].set_title('Figure 1: Navigation_Difficulties when searches were not used')
plt.tight_layout()
plt.show()


df1 = df[df['Searches']== 1.0]

fig,axs=plt.subplots(ncols=2)
fig.set_size_inches(15,5)
sns.histplot(binwidth=0.5, x='Survey_Category', hue = 'TA', data=df1[df1['Survey_Category']== 'Support'], stat="density", multiple="dodge", shrink=.8, ax=axs[0])
sns.histplot(binwidth=0.5, x='Survey_Category', hue = 'Navigation_Difficulties', data=df1[df1['Survey_Category']== 'Support'], stat="density", multiple="dodge", shrink=.8, ax=axs[1])

plt.grid(which='minor', linestyle=':', linewidth='0.5', color='black')

axs[0].set_title('Figure 1: TA when searches were used')
axs[1].set_title('Figure 1: Navigation_Difficulties when searches were used')
plt.tight_layout()
plt.show()


from scipy.stats import chi2_contingency
  
# defining the table
data = [[207, 282, 241], [234, 242, 232]]
stat, p, dof, expected = chi2_contingency(data)
  
# interpret p-value
alpha = 0.05
print("p value is " + str(p))
if p <= alpha:
    print('Dependent (reject H0)')
else:
    print('Independent (H0 holds true)')

p value is 0.1031971404730939
Independent (H0 holds true)


rcParams['figure.figsize'] = 20, 8
sns.histplot(binwidth=0.5, y="Product", hue="TA", data=df.sort_values(by = 'TA', ascending = True), stat="density", multiple="dodge", shrink=.8)
plt.xlabel("Percentage");


df[['Time Spent per Visit (seconds)', 'Platform']].groupby("Platform").mean().sort_values(ascending = True, by = 'Time Spent per Visit (seconds)').plot(kind = 'barh')

<AxesSubplot:ylabel='Platform'>


plt.figure(figsize=(20, 14))

for e, column in enumerate(['Time Spent per Visit (seconds)', 'Searches', 'Average Page Depth', 'Page Events',
                           'event_count', 'page_loads', 'link_clicks']):
    plt.subplot(4, 3, e + 1)
    sns.barplot( data=df, x='Platform', y=column, palette="husl")


plt.figure(figsize=(20, 14))

for e, column in enumerate(['CSAT', 'Navigation_Difficulties']):
    plt.subplot(4, 3, e + 1)
    #sns.lineplot( data=df.reset_index(), x=column, y='TA', palette="husl", y = df.reset_index().loc[df.reset_index()['Survey_Category'] == "Support"]['Survey_Category'])
    sns.histplot(binwidth=0.5, x=column , hue="Navigation_Difficulties", data = df.reset_index().loc[df.reset_index()['Survey_Category'] == "Support"], stat="density", multiple="dodge")
    plt.ylabel("Percentage");


df[['Time Spent per Visit (seconds)', 'Platform']].groupby("Platform").mean().sort_values(ascending = True, by = 'Time Spent per Visit (seconds)').plot(kind = 'barh')
plt.title("Time spent on page against the platform");


df[['Searches', 'Platform']].groupby("Platform").mean().sort_values(ascending = True, by = 'Searches').plot(kind = 'barh')
plt.title("Searches against the platform");


rcParams['figure.figsize'] = 20, 8
sns.histplot(binwidth=0.5, y="Product", hue="Navigation_Difficulties", data=df.sort_values(by = 'TA', ascending = False), stat="density", multiple="dodge", shrink=.8)
plt.xlabel("Percentage");


sns.histplot(binwidth=0.5, y="Platform", hue="TA", data=df, stat="density", multiple="dodge", shrink=.8)
plt.xlabel("Percentage");


sns.histplot(binwidth=0.5, y="Platform", hue="Navigation_Difficulties", data=df, stat="density", multiple="dodge", shrink=.8)
plt.xlabel("Percentage");


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='Navigation_Difficulties',y='CSAT',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='CSAT'>


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='TA',y='CSAT',data=df)

<AxesSubplot:xlabel='TA', ylabel='CSAT'>


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='TA',y='Effort',data=df)

<AxesSubplot:xlabel='TA', ylabel='Effort'>


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='Navigation_Difficulties',y='Effort',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='Effort'>


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='TA',y='Relevance',data=df)

<AxesSubplot:xlabel='TA', ylabel='Relevance'>


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='Navigation_Difficulties',y='Relevance',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='Relevance'>


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='TA',y='Time Spent per Visit (seconds)',data=df)

<AxesSubplot:xlabel='TA', ylabel='Time Spent per Visit (seconds)'>


rcParams['figure.figsize'] = 15, 5
sns.barplot(x='Navigation_Difficulties',y='Time Spent per Visit (seconds)',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='Time Spent per Visit (seconds)'>


selected_features = df[['Product', 'Platform', 'CSAT', 'TA',
       'Effort', 'Navigation_Difficulties', 'Relevance', 'called_flag', 'event_count', 'page_loads', 'link_clicks',
       'impressions', 'Searches', 'Page Events', 'Page Views',
       'Average Page Depth', 'Reloads', 'Time Spent per Visit (seconds)']]


#The features with missing values
total = selected_features.isnull().sum().sort_values(ascending=False)
missing_data = pd.DataFrame(total, columns = ["Missing Values"])
missing_data


## features with missing values
df1 = df[['Average Page Depth', 'Time Spent per Visit (seconds)', 'Reloads',
       'Page Views', 'Page Events', 'Searches', 'page_loads', 'impressions',
       'link_clicks', 'event_count']]
for feature in df1:
    mean = selected_features[feature].mean()
    std = selected_features[feature].std()
    is_null = selected_features[feature].isnull().sum()
    # Get random numbers between the mean, std and is_null
    rand_age = np.random.randint(mean - std, mean + std, size = is_null)
    # fill NaN values in each feature column with random values generated
    feature_slice = selected_features[feature].copy()
    feature_slice[np.isnan(feature_slice)] = rand_age
    selected_features[feature] = feature_slice
##Check if any column still contain missing values
selected_features[feature].isnull().sum()

0


top8_products = df.Product.value_counts().sort_values(ascending = False)[:10]
top8_products

Wireless                                                                                                                   4313
BB                                                                                                                         1706
DTV                                                                                                                         590
Other                                                                                                                       539
Other services from AT&T (Home phone, DSL, etc.)                                                                            300
Other services from AT&T (Home phone, DSL,etc.)                                                                              93
WatchTV                                                                                                                      57
ATT TV                                                                                                                       41
DIRECTV or DIRECTV bundled with other AT&T services (TV delivered by satellite dish)_OLD                                      1
AT&T TVSM or AT&T TVSM bundled with other AT&T services (streamed programming through a special receiver from AT&T)_OLD       1
Name: Product, dtype: int64


top_15_tasks = df.main_task.value_counts().sort_values(ascending = False)[:15]
top_15_tasks

Make a payment                                                                                           1580
Other                                                                                                    1002
View current bill                                                                                         849
Troubleshooting - fix a problem with my device or service                                                 637
Add, change or downgrade plans and features (e.g. International plans, data plans, TV packages, etc.)     338
Check usage                                                                                               287
Update payment method                                                                                     237
Set up or manage Access ID/website profile (includes linking/unlinking accounts)                          232
View previous bill(s)                                                                                     204
Billing, payment and usage help - pay, review or dispute charges                                          194
Make a payment arrangement                                                                                189
Set up or manage email account (includes email password resets)                                           188
Set up/activate products or services                                                                      162
Contact AT&T Customer Service                                                                             160
Contact AT&T Customer Service - find phone numbers, see chat options, locate AT&T stores                  135
Name: main_task, dtype: int64


df = df.loc[df['main_task'].isin(list(top_15_tasks.index))]
df = df.loc[df['main_task'].isin(list(top8_products.index))]


selected_features = df[['TA','called_flag', 'event_count', 'page_loads','Searches', 
                        'Page Events', 'Page Views','Average Page Depth', 'Reloads', 
                        'Time Spent per Visit (seconds)']]


total = selected_features.isnull().sum().sort_values(ascending=False)
missing_data = pd.DataFrame(total, columns = ["Missing Values"])
missing_data


selected_features.select_dtypes('object')


for feature in selected_features.select_dtypes('object'):
    print(feature)
    selected_features[feature] = pd.factorize(selected_features[feature])[0]

TA


## features with missing values
df1 = df[['Average Page Depth', 'Time Spent per Visit (seconds)', 'Reloads',
       'Page Views', 'Page Events', 'Searches', 'page_loads', 'event_count']]
for feature in df1:
    mean = selected_features[feature].mean()
    std = selected_features[feature].std()
    is_null = selected_features[feature].isnull().sum()
    # Get random numbers between the mean, std and is_null
    rand_age = np.random.randint(mean - std, mean + std, size = is_null)
    # fill NaN values in each feature column with random values generated
    feature_slice = selected_features[feature].copy()
    feature_slice[np.isnan(feature_slice)] = rand_age
    selected_features[feature] = feature_slice
##Check if any column still contain missing values
selected_features[feature].isnull().sum()

0


## Selecting 3 boolean features and two population features
X = selected_features.drop('TA', axis = 1)
y = selected_features['TA']

oversample = SMOTE()
X, y = oversample.fit_resample(X, y)

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.tree import DecisionTreeClassifier
# define the model
model = DecisionTreeClassifier()
# fit the model
model.fit(X_train, y_train)
y_pred_tr = model.predict(X_train)
y_pred = model.predict(X_test)


print("Accuracy score for training data", accuracy_score(y_train, y_pred_tr, normalize=True))
print("Accuracy score for test data", accuracy_score(y_test, y_pred, normalize=True))

Accuracy score for training data 0.9990157480314961
Accuracy score for test data 0.6023622047244095


from sklearn.metrics import confusion_matrix
conf = confusion_matrix(y_test, y_pred)

print (classification_report(y_test, y_pred))
plt.figure(figsize=(9,6))


sns.heatmap(conf,annot=True, annot_kws={"size": 16}, fmt="d", cmap=plt.cm.Reds)

              precision    recall  f1-score   support

           0       0.60      0.55      0.57       123
           1       0.61      0.65      0.63       131

    accuracy                           0.60       254
   macro avg       0.60      0.60      0.60       254
weighted avg       0.60      0.60      0.60       254

<AxesSubplot:>


### Set survey category as target variable
X = df[['Time Spent per Visit (seconds)']]
y = df['Navigation_Difficulties']

from sklearn.tree import DecisionTreeClassifier
# define the model
model = DecisionTreeClassifier()
# fit the model
model.fit(X, y)


fig = plt.figure(figsize=(25, 20))
_ = tree.plot_tree(model, 
                   feature_names=X.columns,  
                   class_names=["1", "0"],
                   filled=True)


### Set survey category as target variable
X = df[['Time Spent per Visit (seconds)']]
y = df['TA']

from sklearn.tree import DecisionTreeClassifier
# define the model
model = DecisionTreeClassifier()
# fit the model
model.fit(X, y)
fig =  plt.figure(figsize=(10, 10))
_ = tree.plot_tree(model, 
                   feature_names=X.columns,  
                   class_names=["1", "0"],
                   filled=True)


# Compute confusion matrix
from sklearn.metrics import *

cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)

print (classification_report(y_test, y_pred))
plt.figure(figsize=(9,6))


sns.heatmap(cnf_matrix,annot=True, annot_kws={"size": 16}, fmt="d", cmap=plt.cm.Reds)

              precision    recall  f1-score   support

           0       0.60      0.55      0.57       123
           1       0.61      0.65      0.63       131

    accuracy                           0.60       254
   macro avg       0.60      0.60      0.60       254
weighted avg       0.60      0.60      0.60       254

<AxesSubplot:>


selected_features['TA'] = pd.factorize(selected_features['TA'])[0]


#Let's visualize correlations

plt.figure(figsize=(20,10))
cor = selected_features.corr()
heatmap = sns.heatmap(cor
                      , vmin=-1, vmax=1, annot=True, cmap='BrBG')
heatmap.set_title('Features Correlation with Task Accomplishment', fontdict={'fontsize':18}, pad=16);


#Correlation with output variable
cor_target = abs(cor['TA'])
#Selecting highly correlated features
relevant_features = cor_target.sort_values(ascending = False)
## Top 6 featurs with high correlation
relevant_features[:6]

TA                                1.000000
event_count                       0.068686
Page Views                        0.043329
page_loads                        0.031152
Searches                          0.030907
Time Spent per Visit (seconds)    0.028977
Name: TA, dtype: float64


# Oversample with SMOTE and random undersample for imbalanced dataset
from collections import Counter
from sklearn.datasets import make_classification
from imblearn.over_sampling import SMOTE
from imblearn.under_sampling import RandomUnderSampler
from imblearn.pipeline import Pipeline
from matplotlib import pyplot
from numpy import where
# define dataset
X, y = make_classification(n_samples=10000, n_features=2, n_redundant=0,
	n_clusters_per_class=1, weights=[0.99], flip_y=0, random_state=1)
# summarize class distribution
counter = Counter(y)
print(counter)
# define pipeline
over = SMOTE(sampling_strategy=0.1)
under = RandomUnderSampler(sampling_strategy=0.5)
steps = [('o', over), ('u', under)]
pipeline = Pipeline(steps=steps)
# transform the dataset
X, y = pipeline.fit_resample(X, y)
# summarize the new class distribution
counter = Counter(y)
print(counter)
# scatter plot of examples by class label
for label, _ in counter.items():
	row_ix = where(y == label)[0]
	pyplot.scatter(X[row_ix, 0], X[row_ix, 1], label=str(label))
pyplot.legend()
pyplot.show()

Counter({0: 9900, 1: 100})
Counter({0: 1980, 1: 990})


rcParams['figure.figsize'] = 15, 5
sns.lineplot(x='Navigation_Difficulties',y='Time Spent per Visit (seconds)',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='Time Spent per Visit (seconds)'>


df.groupby('Navigation_Difficulties')['Time Spent per Visit (seconds)'].describe()


rcParams['figure.figsize'] = 15, 5
sns.lineplot(x='TA',y='Time Spent per Visit (seconds)',data=df)

<AxesSubplot:xlabel='TA', ylabel='Time Spent per Visit (seconds)'>


df.groupby('TA')['Time Spent per Visit (seconds)'].describe()


df.groupby('Navigation_Difficulties')['Average Page Depth'].describe()


df.groupby('TA')['Average Page Depth'].describe()


rcParams['figure.figsize'] = 15, 5
sns.lineplot(x='Navigation_Difficulties',y='Average Page Depth',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='Average Page Depth'>


rcParams['figure.figsize'] = 15, 5
sns.lineplot(x='TA',y='Average Page Depth',data=df)

<AxesSubplot:xlabel='TA', ylabel='Average Page Depth'>


rcParams['figure.figsize'] = 15, 5
sns.lineplot(x='Navigation_Difficulties',y='Page Events',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='Page Events'>


df.groupby('Navigation_Difficulties')['Page Events'].describe()


rcParams['figure.figsize'] = 15, 5
sns.lineplot(x='Navigation_Difficulties',y='Page Views',data=df)

<AxesSubplot:xlabel='Navigation_Difficulties', ylabel='Page Views'>


df.groupby('Navigation_Difficulties')['Page Views'].describe()


df.Navigation_Difficulties.unique()

array(['Yes', 'No'], dtype=object)


df.head()


plt.figure(figsize=(15, 5))

#for e, column in enumerate(['TA', 'Navigation_Difficulties']):
#plt.subplot(3, 2, e + 1)
g = sns.barplot(data=df, x="TA", y="CSAT")
g.set_xticklabels([ 'Use Search', 'Did not use search'],
       rotation=20)
plt.ylabel('Frequency')
plt.title("Navigation Success");


sns.countplot(y="Platform", hue="Navigation_Difficulties", data=df)
plt.title("Navigation by Platform")

Text(0.5, 1.0, 'Navigation by Platform')


sns.countplot(y="Platform", hue="TA", data=df)
plt.title("Task Acccomplishment by Platform")

Text(0.5, 1.0, 'Task Acccomplishment by Platform')


rcParams['figure.figsize'] = 18, 6
sns.countplot(y="Product", hue="Navigation_Difficulties", data=df)
plt.title("Navigation Difficulties by Product")

Text(0.5, 1.0, 'Navigation Difficulties by Product')


rcParams['figure.figsize'] = 18, 6
sns.countplot(y="Product", hue="TA", data=df)
plt.title("Task accomplishment by Product")

Text(0.5, 1.0, 'Task accomplishment by Product')


df.columns

Index(['foresee_respondent', 'foresee_session_id', 'wt_visitor_id', 'day',
       'Survey_Category', 'Product', 'Platform', 'main_task', 'CSAT', 'TA',
       'Effort', 'Navigation_Difficulties', 'Relevance', 'called_flag',
       'app_session_id', 'event_count', 'page_loads', 'link_clicks',
       'impressions', 'urls', 'Searches', 'Page Events', 'Page Views',
       'Average Page Depth', 'Reloads', 'Time Spent per Visit (seconds)',
       'Search'],
      dtype='object')


## Updating selected features
selected_features_2 = df[['called_flag', 'event_count', 'page_loads','Searches', 
                        'Page Events', 'Page Views','Average Page Depth', 'Reloads', 
                        'Time Spent per Visit (seconds)']].dropna()


### Set survey category as target variable
X = selected_features_2.drop(['Reloads'], axis = 1)
y = selected_features_2['Reloads']

oversample = SMOTE()
X, y = oversample.fit_resample(X, y)

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.tree import DecisionTreeClassifier
# define the model
model = DecisionTreeClassifier()
# fit the model
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_pred_tr = model.predict(X_train)

print("Accuracy score for training data", accuracy_score(y_train, y_pred_tr, normalize=True))
print("Accuracy score for test data", accuracy_score(y_test, y_pred, normalize=True))

# summarize feature importance
imp = pd.DataFrame()

imp["var"] = X.columns

importance = model.feature_importances_

imp["imp"] = importance

imp = imp.sort_values("imp", ascending = False).reset_index(drop = True)

# PRINT OUT THE DATA FRAME
imp.sort_values(by = 'imp', ascending = True).plot.barh(x='var', y='imp', ).figsize=(15, 5)
plt.title("Feature importance plot for Decision Tree Model (Survey Category)")

Accuracy score for training data 1.0
Accuracy score for test data 0.7370753323485968

Text(0.5, 1.0, 'Feature importance plot for Decision Tree Model (Survey Category)')


# Compute confusion matrix
from sklearn.metrics import *

cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)

print (classification_report(y_test, y_pred))
plt.figure(figsize=(9,6))


sns.heatmap(cnf_matrix,annot=True, annot_kws={"size": 16}, fmt="d", cmap=plt.cm.Reds)

              precision    recall  f1-score   support

         0.0       0.69      0.56      0.62       131
         1.0       0.59      0.62      0.61       113
         2.0       0.69      0.68      0.68       118
         3.0       0.75      0.78      0.76        98
         4.0       0.81      0.88      0.84       106
         5.0       0.89      0.95      0.92       111

    accuracy                           0.74       677
   macro avg       0.74      0.75      0.74       677
weighted avg       0.73      0.74      0.73       677

<AxesSubplot:>


df.groupby('Survey_Category')['page_loads'].describe()


df.groupby('Survey_Category')['Time Spent per Visit (seconds)'].describe()


df.groupby('Survey_Category')['Page Events'].describe()


df.groupby('Survey_Category')['Average Page Depth'].describe()


df.groupby('Survey_Category')['Reloads'].describe()


## Updating selected features
selected_features_3 = df[['called_flag', 'event_count', 'page_loads','Searches', "Product",
                        'Page Events', 'Page Views','Average Page Depth', 'Reloads', 
                        'Time Spent per Visit (seconds)']].dropna()


### Set Product as target variable
X = selected_features_3.drop(['Product'], axis = 1)
y = selected_features_3['Product']

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.tree import DecisionTreeClassifier
# define the model
model = DecisionTreeClassifier()
# fit the model
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_pred_tr = model.predict(X_train)

print("Accuracy score for training data", accuracy_score(y_train, y_pred_tr, normalize=True))
print("Accuracy score for test data", accuracy_score(y_test, y_pred, normalize=True))

# summarize feature importance
imp = pd.DataFrame()

imp["var"] = X.columns

importance = model.feature_importances_

imp["imp"] = importance

imp = imp.sort_values("imp", ascending = False).reset_index(drop = True)

# PRINT OUT THE DATA FRAME
imp.sort_values(by = 'imp', ascending = True).plot.barh(x='var', y='imp', ).figsize=(15, 5)
plt.title("Feature importance plot for Decision Tree Model (Product)")

Accuracy score for training data 0.9987515605493134
Accuracy score for test data 0.373134328358209

Text(0.5, 1.0, 'Feature importance plot for Decision Tree Model (Product)')


# Compute confusion matrix
from sklearn.metrics import *

cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)

print (classification_report(y_test, y_pred))
plt.figure(figsize=(9,6))


sns.heatmap(cnf_matrix,annot=True, annot_kws={"size": 16}, fmt="d", cmap=plt.cm.Reds)

                                                  precision    recall  f1-score   support

                                          ATT TV       0.00      0.00      0.00         4
                                              BB       0.10      0.16      0.12        32
                                             DTV       0.16      0.21      0.18        14
                                           Other       0.20      0.20      0.20        20
Other services from AT&T (Home phone, DSL, etc.)       0.00      0.00      0.00        11
 Other services from AT&T (Home phone, DSL,etc.)       0.00      0.00      0.00         3
                                         WatchTV       0.00      0.00      0.00         0
                                        Wireless       0.66      0.54      0.59       117

                                        accuracy                           0.37       201
                                       macro avg       0.14      0.14      0.14       201
                                    weighted avg       0.43      0.37      0.40       201

<AxesSubplot:>


## Updating selected features
selected_features_4 = df[['called_flag', 'event_count', 'page_loads','Searches', "Platform",
                        'Page Events', 'Page Views','Average Page Depth', 'Reloads', 
                        'Time Spent per Visit (seconds)']].dropna()


### Set Platform as target variable
X = selected_features_4.drop(['Platform'], axis = 1)
y = selected_features_4['Platform']

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.tree import DecisionTreeClassifier
# define the model
model = DecisionTreeClassifier()
# fit the model
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_pred_tr = model.predict(X_train)

print("Accuracy score for training data", accuracy_score(y_train, y_pred_tr, normalize=True))
print("Accuracy score for test data", accuracy_score(y_test, y_pred, normalize=True))

# summarize feature importance
imp = pd.DataFrame()

imp["var"] = X.columns

importance = model.feature_importances_

imp["imp"] = importance

imp = imp.sort_values("imp", ascending = False).reset_index(drop = True)

# PRINT OUT THE DATA FRAME
imp.sort_values(by = 'imp', ascending = True).plot.barh(x='var', y='imp', ).figsize=(15, 5)
plt.title("Feature importance plot for Decision Tree Model (Platform)")

Accuracy score for training data 1.0
Accuracy score for test data 0.572139303482587

Text(0.5, 1.0, 'Feature importance plot for Decision Tree Model (Platform)')


# Compute confusion matrix
from sklearn.metrics import *

cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)

print (classification_report(y_test, y_pred))
plt.figure(figsize=(9,6))


sns.heatmap(cnf_matrix,annot=True, annot_kws={"size": 16}, fmt="d", cmap=plt.cm.Reds)

              precision    recall  f1-score   support

         App       0.70      0.68      0.69        63
     Desktop       0.61      0.60      0.61        98
  Mobile Web       0.30      0.33      0.31        40

    accuracy                           0.57       201
   macro avg       0.54      0.54      0.54       201
weighted avg       0.58      0.57      0.57       201

<AxesSubplot:>


df.groupby('Platform')['Time Spent per Visit (seconds)'].describe()


df.groupby('Platform')['page_loads'].describe()


df.groupby('Platform')['Page Events'].describe()


df.groupby('Platform')['Average Page Depth'].describe()


df.groupby('Platform')['Reloads'].describe()


selected_features_5 = df[['event_count', 'page_loads','Searches', "Navigation_Difficulties",
                        'Page Events', 'Page Views','Average Page Depth', 'Reloads', 
                        'Time Spent per Visit (seconds)']].dropna()


selected_features_5['Navigation_Difficulties'] = pd.factorize(selected_features_5["Navigation_Difficulties"])[0]


#Let's visualize correlations
plt.figure(figsize=(20,10))
cor = selected_features_5.corr()
heatmap = sns.heatmap(cor
                      , vmin=-1, vmax=1, annot=True, cmap='BrBG')
heatmap.set_title('Features Correlation with Navigation Difficulties', fontdict={'fontsize':18}, pad=16);


#Correlation with output variable
cor_target = abs(cor['Navigation_Difficulties'])


#Selecting highly correlated features
relevant_features = cor_target.sort_values(ascending = False)
## Top 6 featurs with high correlation
relevant_features[:6]

Navigation_Difficulties           1.000000
event_count                       0.082212
Average Page Depth                0.062015
Searches                          0.037833
Time Spent per Visit (seconds)    0.015807
Page Events                       0.012196
Name: Navigation_Difficulties, dtype: float64


### Set survey category as target variable
X = selected_features_5.drop(['Navigation_Difficulties'], axis = 1)
y = selected_features_5['Navigation_Difficulties']

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.ensemble import RandomForestClassifier
# define the model
model = RandomForestClassifier()
# fit the model
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
y_pred_tr = model.predict(X_train)

print("Accuracy score for training data", accuracy_score(y_train, y_pred_tr, normalize=True))
print("Accuracy score for test data", accuracy_score(y_test, y_pred, normalize=True))

# summarize feature importance
imp = pd.DataFrame()

imp["var"] = X.columns

importance = model.feature_importances_

imp["imp"] = importance

imp = imp.sort_values("imp", ascending = False).reset_index(drop = True)

# PRINT OUT THE DATA FRAME
imp.sort_values(by = 'imp', ascending = True).plot.barh(x='var', y='imp', ).figsize=(15, 5)
plt.title("Feature importance plot for Random Forest Model (Navigation Difficulties)")

Accuracy score for training data 0.9987515605493134
Accuracy score for test data 0.5223880597014925

Text(0.5, 1.0, 'Feature importance plot for Random Forest Model (Navigation Difficulties)')


# Compute confusion matrix
from sklearn.metrics import *

cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)

print (classification_report(y_test, y_pred))
plt.figure(figsize=(9,6))


sns.heatmap(cnf_matrix,annot=True, annot_kws={"size": 16}, fmt="d", cmap=plt.cm.Reds)

              precision    recall  f1-score   support

           0       0.52      0.66      0.58       101
           1       0.53      0.38      0.44       100

    accuracy                           0.52       201
   macro avg       0.52      0.52      0.51       201
weighted avg       0.52      0.52      0.51       201

<AxesSubplot:>


### Set survey category as target variable
X = selected_features_5.drop(['Navigation_Difficulties'], axis = 1)
y = selected_features_5['Navigation_Difficulties']

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.neighbors import KNeighborsClassifier
# define the model

from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS

# summarize feature importance
iris = pd.DataFrame()
X = selected_features_5.drop(['Navigation_Difficulties'], axis = 1)
y = selected_features_5['Navigation_Difficulties']

knn = KNeighborsClassifier(n_neighbors=3)

efs1 = EFS(knn, 
           min_features=1,
           max_features=4,
           scoring='accuracy',
           print_progress=True,
           cv=5)

efs1 = efs1.fit(X, y)

print('Best accuracy score: %.2f' % efs1.best_score_)
print('Best subset (indices):', efs1.best_idx_)
print('Best subset (corresponding names):', efs1.best_feature_names_)

Features: 162/162

Best accuracy score: 0.57
Best subset (indices): (2, 3, 5, 6)
Best subset (corresponding names): ('Searches', 'Page Events', 'Average Page Depth', 'Reloads')


y_pred_tr = model.predict(X_train)

print("Accuracy score for training data", accuracy_score(y_train, y_pred_tr, normalize=True))
print("Accuracy score for test data", accuracy_score(y_test, y_pred, normalize=True))

Accuracy score for training data 0.9987515605493134
Accuracy score for test data 0.5223880597014925


# Compute confusion matrix
from sklearn.metrics import *

cnf_matrix = confusion_matrix(y_test, y_pred)
np.set_printoptions(precision=2)

print (classification_report(y_test, y_pred))
plt.figure(figsize=(9,6))


sns.heatmap(cnf_matrix,annot=True, annot_kws={"size": 16}, fmt="d", cmap=plt.cm.Reds)

              precision    recall  f1-score   support

           0       0.52      0.66      0.58       101
           1       0.53      0.38      0.44       100

    accuracy                           0.52       201
   macro avg       0.52      0.52      0.51       201
weighted avg       0.52      0.52      0.51       201

<AxesSubplot:>


df.groupby('Navigation_Difficulties')['Time Spent per Visit (seconds)'].describe()


df.groupby('Navigation_Difficulties')['Average Page Depth'].describe()


X = selected_features_5.drop(['Navigation_Difficulties'], axis = 1)
y = selected_features_5['Navigation_Difficulties']


## k_features tells us how many features should be selected. 
#We’ve passed 4 so the model will train until 4 features are selected.
from sklearn.ensemble import RandomForestClassifier
from mlxtend.feature_selection import SequentialFeatureSelector as sfs
RF = RandomForestClassifier()
fs1 = sfs(RF, k_features=4, forward=True, verbose=2, scoring='balanced_accuracy')


fs1 = fs1.fit(X, y)

[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    1.9s remaining:    0.0s
[Parallel(n_jobs=1)]: Done   8 out of   8 | elapsed:   16.0s finished

[2022-08-05 02:00:35] Features: 1/4 -- score: 0.54217240710479[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    2.1s remaining:    0.0s
[Parallel(n_jobs=1)]: Done   7 out of   7 | elapsed:   15.3s finished

[2022-08-05 02:00:50] Features: 2/4 -- score: 0.5488806610308341[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    2.3s remaining:    0.0s
[Parallel(n_jobs=1)]: Done   6 out of   6 | elapsed:   13.7s finished

[2022-08-05 02:01:04] Features: 3/4 -- score: 0.5437098823413916[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    2.7s remaining:    0.0s
[Parallel(n_jobs=1)]: Done   5 out of   5 | elapsed:   12.7s finished

[2022-08-05 02:01:17] Features: 4/4 -- score: 0.5576166780803475


feat_names = list(fs1.k_feature_names_)
print(feat_names)

['Searches', 'Page Events', 'Average Page Depth', 'Time Spent per Visit (seconds)']


### Set survey category as target variable
X = selected_features_5.drop(['Navigation_Difficulties'], axis = 1)
y = selected_features_5['Navigation_Difficulties']

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.neighbors import KNeighborsClassifier
# define the model
from sklearn.datasets import load_iris
from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS

# summarize feature importance
iris = pd.DataFrame()
X = selected_features_5.drop(['Navigation_Difficulties'], axis = 1)
y = selected_features_5['Navigation_Difficulties']

knn = KNeighborsClassifier(n_neighbors=3)

efs1 = EFS(knn, 
           min_features=1,
           max_features=4,
           scoring='accuracy',
           print_progress=True,
           cv=5)

efs1 = efs1.fit(X, y)

print('Best accuracy score: %.2f' % efs1.best_score_)
print('Best subset (indices):', efs1.best_idx_)
print('Best subset (corresponding names):', efs1.best_feature_names_)

Features: 162/162

Best accuracy score: 0.57
Best subset (indices): (2, 3, 5, 6)
Best subset (corresponding names): ('Searches', 'Page Events', 'Average Page Depth', 'Reloads')


### Set survey category as target variable
X = selected_features.drop('TA', axis = 1)
y = selected_features['TA']

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.neighbors import KNeighborsClassifier
# define the model

from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS

# summarize feature importance
iris = pd.DataFrame()
X = selected_features.drop('TA', axis = 1)
y = selected_features['TA']

knn = KNeighborsClassifier(n_neighbors=3)

efs1 = EFS(knn, 
           min_features=1,
           max_features=4,
           scoring='accuracy',
           print_progress=True,
           cv=5)

efs1 = efs1.fit(X, y)

print('Best accuracy score: %.2f' % efs1.best_score_)
print('Best subset (indices):', efs1.best_idx_)
print('Best subset (corresponding names):', efs1.best_feature_names_)

Features: 255/255

Best accuracy score: 0.63
Best subset (indices): (0,)
Best subset (corresponding names): ('called_flag',)


import matplotlib.pyplot as plt

metric_dict = efs1.get_metric_dict()

fig = plt.figure()
k_feat = sorted(metric_dict.keys())
avg = [metric_dict[k]['avg_score'] for k in k_feat]

upper, lower = [], []
for k in k_feat:
    upper.append(metric_dict[k]['avg_score'] +
                 metric_dict[k]['std_dev'])
    lower.append(metric_dict[k]['avg_score'] -
                 metric_dict[k]['std_dev'])

plt.fill_between(k_feat,
                 upper,
                 lower,
                 alpha=0.2,
                 color='blue',
                 lw=1)

plt.plot(k_feat, avg, color='blue', marker='o')
plt.ylabel('Accuracy +/- Standard Deviation')
plt.xlabel('Number of Features')
feature_min = len(metric_dict[k_feat[0]]['feature_idx'])
feature_max = len(metric_dict[k_feat[-1]]['feature_idx'])
plt.xticks(k_feat, 
           [str(metric_dict[k]['feature_names']) for k in k_feat], 
           rotation=90)
plt.show()


df5 = pd.read_csv("error_codes.csv")
df5.head()


df6 = pd.read_csv("searches.csv")
df6.head()


merged = pd.merge(left=df5, right=df6, left_on='FORESEE_SESSION', right_on='foresee_session')


df = pd.merge(left=merged, right=df, left_on='FORESEE_SESSION', right_on='foresee_session_id')
df


df.to_csv('Merged_file.csv', index = False)


def clean_text(text):
#will replace the html characters with " "
    text=re.sub('<.*?>', ' ', text)  
    text = re.sub('[^a-zA-Z]',' ',text)
    #will replace newline with space
    text = re.sub("\n"," ",text)
    #will convert to lower case
    text = text.lower()
    # will split and join the words
    text=' '.join(text.split())
    return text


### Apply data cleaning on text feature in our data
df6['search_terms'] = df6['search_terms'].apply(lambda x : clean_text(x))
df6['search_terms']

0             where can i find the password for my router
1       i do not have auto pay and some one debited my...
2                                       recycle equipment
3       internet security suite download internet secu...
4       att sent me a text saying that you are giving ...
                              ...                        
8371    reset voicemail password set up my cellphone v...
8372                                     need to pay bill
8373                                        talk to a rep
8374    is there fiber at my house is there fiber at m...
8375                                        my phone bill
Name: search_terms, Length: 8376, dtype: object


## Search Terms that led to Navigation Difficulties


navigation_success = df.loc[df['Navigation_Difficulties'] == 'Yes']


from wordcloud import WordCloud, STOPWORDS

wordcloud = WordCloud(stopwords=STOPWORDS,
                      background_color='white',
                      width=1200,
                      height=1000).generate(str(navigation_success['search_terms']))


plt.figure( figsize=(8,6) )
plt.imshow(wordcloud)
plt.title('Frequent words in our search_terms')
plt.axis('off')
plt.show()


from collections import Counter
p = Counter(navigation_success['search_terms']).most_common(10)
rslt = pd.DataFrame(p, columns=['Word', 'Frequency'])
print(rslt)

                                                Word  Frequency
0                                        appointment          1
1         signature program enrollment,  fan 5339885          1
2                                           discount          1
3                                        email login          1
4        connectivity program,  connectivity program          1
5    i wanna change my wi-fi password,  i wanna c...          1
6    contact information,  contact information,  ...          1
7                      employee and retiree discount          1
8    receive free at&t cell booster because of up...          1
9                                         anti virus          1


### Error codes
from collections import Counter
p = Counter(navigation_success['ERROR_CODES']).most_common(10)
rslt = pd.DataFrame(p, columns=['Error code', 'Frequency'])
print(rslt)

                           Error code  Frequency
0                                0,-2          3
1                                  -2          2
2                                -2,1          2
3                                1,-2          2
4                                 0,1          1
5  205.4,205.2,MSFIDACL08,MSFIDELAG00          1
6                                   1          1
7                               205.4          1
8                        902,201,-2,1          1
9                        902,205.4,-2          1


##Search Terms that led to failure in Task Accomplishment


TA_No = df.loc[df['TA'] == 'No']


from wordcloud import WordCloud, STOPWORDS

wordcloud = WordCloud(stopwords=STOPWORDS,
                      background_color='white',
                      width=1200,
                      height=1000).generate(str(TA_No['search_terms']))


p = Counter(TA_No['search_terms'], ).most_common(10)
rslt = pd.DataFrame(p, columns=['Word', 'Frequency'])
print(rslt)

                                                Word  Frequency
0                                        appointment          1
1         signature program enrollment,  fan 5339885          1
2                                           discount          1
3                                        email login          1
4                        how do i print my statement          1
5    feedback,  feedback,  complaints,  feedback,...          1
6    i wanna change my wi-fi password,  i wanna c...          1
7    contact information,  contact information,  ...          1
8    receive free at&t cell booster because of up...          1
9                                         anti virus          1


### Error codes for Navigation 
from collections import Counter
p = Counter(navigation_success['ERROR_CODES']).most_common(10)
rslt = pd.DataFrame(p, columns=['Error code', 'Frequency'])
print(rslt)

                           Error code  Frequency
0                                0,-2          3
1                                  -2          2
2                                -2,1          2
3                                1,-2          2
4                                 0,1          1
5  205.4,205.2,MSFIDACL08,MSFIDELAG00          1
6                                   1          1
7                               205.4          1
8                        902,201,-2,1          1
9                        902,205.4,-2          1


### Error codes for Task Accomplishment

p = Counter(TA_No['ERROR_CODES']).most_common(10)
rslt = pd.DataFrame(p, columns=['Error code', 'Frequency'])
print(rslt)

                           Error code  Frequency
0                                0,-2          3
1                                  -2          2
2                                   0          2
3                                1,-2          2
4                                 0,1          1
5  205.4,205.2,MSFIDACL08,MSFIDELAG00          1
6                      0,LGN_02_07,-2          1
7                                   1          1
8                               205.4          1
9                        902,201,-2,1          1


navigation_failure = df.loc[df['Navigation_Difficulties'] == 'No']

from wordcloud import WordCloud, STOPWORDS

wordcloud = WordCloud(stopwords=STOPWORDS,
                      background_color='white',
                      width=1200,
                      height=1000).generate(str(navigation_failure['search_terms']))


plt.figure( figsize=(8,6) )
plt.imshow(wordcloud)
plt.title('Frequent words in our search_terms')
plt.axis('off')
plt.show()


from collections import Counter
p = Counter(navigation_failure['search_terms']).most_common(10)
rslt = pd.DataFrame(p, columns=['Word', 'Frequency'])
print(rslt)

                                                Word  Frequency
0                        how do i print my statement          1
1                                        reward card          1
2    feedback,  feedback,  complaints,  feedback,...          1
3                                       unlock phone          1
4                                             unlimi          1
5                                   report text spam          1
6        transfer number to another carrier,  unlock          1
7                                            suspend          1
8                                      international          1
9                                               chat          1


### Error codes

p = Counter(navigation_failure['ERROR_CODES']).most_common(10)
rslt = pd.DataFrame(p, columns=['Error code', 'Frequency'])
print(rslt)

       Error code  Frequency
0               0          2
1            -2,1          2
2            1,-2          2
3          201,-2          1
4  0,LGN_02_07,-2          1
5        -2,1,201          1
6         0,201,1          1
7      0,1,201,-2          1
8              -2          1
9          -2,201          1


##Search Terms that led to Task Accomplishment

TA_Yes = df.loc[df['TA'] == 'Yes']


from wordcloud import WordCloud, STOPWORDS

wordcloud = WordCloud(stopwords=STOPWORDS,
                      background_color='white',
                      width=1200,
                      height=1000).generate(str(TA_Yes['search_terms']))


p = Counter(TA_Yes['search_terms']).most_common(10)
rslt = pd.DataFrame(p, columns=['Search Terms', 'Frequency'])
print(rslt)

                                    Search Terms  Frequency
0    connectivity program,  connectivity program          1
1                                    reward card          1
2                                   unlock phone          1
3                                         unlimi          1
4                  employee and retiree discount          1
5                               report text spam          1
6    transfer number to another carrier,  unlock          1
7                                        suspend          1
8                                  international          1
9                                     voice mail          1


### Error codes

p = Counter(TA_Yes['ERROR_CODES']).most_common(10)
rslt = pd.DataFrame(p, columns=['Error code', 'Frequency'])
print(rslt)

   Error code  Frequency
0        -2,1          3
1        1,-2          2
2          -2          1
3      201,-2          1
4    -2,1,201          1
5           0          1
6     0,201,1          1
7  0,1,201,-2          1


# Initialize the dataset

from sklearn.neighbors import KNeighborsClassifier
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

iris = load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(
         X, y, test_size=0.33, random_state=1)

knn = KNeighborsClassifier(n_neighbors=3)


# Select the "best" three features via
# 5-fold cross-validation on the training set.

from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS

fs1 = EFS(knn, 
           min_features=1,
           max_features=4,
           scoring='accuracy',
           cv=5)
fs1 = fs1.fit(X_train, y_train)

Features: 15/15


print('Selected features:', fs1.best_idx_)

Selected features: (2, 3)


# Generate the new subsets based on the selected features
# Note that the transform call is equivalent to
# X_train[:, fs1.k_feature_idx_]

X_train_fs = fs1.transform(X_train)
X_test_fs = fs1.transform(X_test)

# Fit the estimator using the new feature subset
# and make a prediction on the test data
knn.fit(X_train_fs, y_train)
y_pred = knn.predict(X_test_fs)

# Compute the accuracy of the prediction
acc = float((y_test == y_pred).sum()) / y_pred.shape[0]
print('Test set accuracy: %.2f %%' % (acc*100))

Test set accuracy: 96.00 %


y_pred_tr = knn.predict(X_train_fs)

print("Accuracy score for training data in knn Model", accuracy_score(y_train, y_pred_tr, normalize=True))
print("Accuracy score for test data in knn Model", accuracy_score(y_test, y_pred, normalize=True))

Accuracy score for training data in knn Model 0.96
Accuracy score for test data in knn Model 0.96


df_result = pd.read_csv("result.csv")
df = pd.read_csv("Navigation_Dataset.csv")

## Discard values of each feature that are 2x standard deviation away from the mean values
for feature in df.select_dtypes(include=['int16', 'int32', 'int64', 'float16', 'float32', 'float64']):
    df = df[np.abs(df[feature]-df[feature].mean()) <= (2*df[feature].std())]


df_final = pd.merge(left=df, right=df_result, left_on='foresee_session_id', right_on='FORESEE_SESSION')
df_final


df_final.PAGE_URL.value_counts(ascending = False)[:10].plot(kind = 'barh')
plt.title("Majority of things customers were doing before they clicked on search")

Text(0.5, 1.0, 'Majority of things customers were doing before they clicked on search')


df_final = df_final.loc[df_final['Searches'] != 0.0]

df_final.Searches.value_counts(ascending = True).plot(kind = 'barh')

<AxesSubplot:>


df_final = df_final.dropna()
df_final = df_final[~df_final['PAGE_URL'].str.contains('/support/')]


nd_pu = df_final.groupby(['Navigation_Difficulties','PAGE_URL']).size().reset_index(name='count').\
sort_values(by = 'count', ascending = False).reset_index().drop(['index'], axis = 1)[:40]

## Show top 50 results

plt.figure(figsize=(10,10))

sns.barplot(y = 'PAGE_URL', x = "count", data = nd_pu, hue = 'Navigation_Difficulties')

<AxesSubplot:xlabel='count', ylabel='PAGE_URL'>


TA_PU = df_final.groupby(['TA','PAGE_URL']).size().reset_index(name='count')\
.sort_values(by = 'count', ascending = False).reset_index().drop(['index'], axis = 1)[:40]

## Show top 50 results
plt.figure(figsize=(10,10))

sns.barplot(y = 'PAGE_URL', x = "count", data = TA_PU, hue = 'TA')

<AxesSubplot:xlabel='count', ylabel='PAGE_URL'>


selected_features_5 = df_final[['event_count', 'page_loads','Searches', "Navigation_Difficulties",
                        'Page Events', 'Page Views','Average Page Depth', 'Reloads', 
                        'Time Spent per Visit (seconds)']].dropna()


### Set survey category as target variable
X = selected_features_5.drop(['Searches'], axis = 1)
y = selected_features_5['Searches']

#Split the dataset with 80% data for training and 20% for testing set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)

from sklearn.neighbors import KNeighborsClassifier
# define the model

from mlxtend.feature_selection import ExhaustiveFeatureSelector as EFS

# summarize feature importance
X = selected_features_5.drop(['Searches'], axis = 1)
y = selected_features_5['Searches']

knn = KNeighborsClassifier(n_neighbors=3)

efs1 = EFS(knn, 
           min_features=4,
           max_features=6,
           scoring='accuracy',
           print_progress=True,
           cv=5)

efs1 = efs1.fit(X, y)

print('Best accuracy score: %.2f' % efs1.best_score_)
print('Best subset (indices):', efs1.best_idx_)
print('Best subset (corresponding names):', efs1.best_feature_names_)

Features: 154/154

Best accuracy score: 0.95
Best subset (indices): (0, 1, 4, 6)
Best subset (corresponding names): ('event_count', 'page_loads', 'Page Views', 'Reloads')


fig=plt.figure(figsize=(15,15))

for e, column in enumerate(['event_count', 'page_loads', 'Page Events', 'Time Spent per Visit (seconds)']):
    plt.subplot(4, 3, e + 1)
    sns.regplot( data= df_final, x=column, y='Searches', line_kws={"color": "green"})


#df_final[['PAGE_URL']]
df_final[['Path1','Path2', 'Path3', 'Path4', 'Path5']] = df_final['PAGE_URL'].str.split('/', expand=True)
df_final.head()


df_final[['Path6', 'Path7']] = df_final['urls'].str.split('/', expand=True).iloc[:, [14,17]]

df_final[['Path2', 'Path3', 'Path4', 'Path5', 'Path6', 'Path7']] = df_final[['Path2', 'Path3', 'Path4', 'Path5','Path6', 'Path7']].replace(to_replace=[None], value=np.nan)
df_final[['Path2', 'Path3', 'Path4', 'Path5','Path6', 'Path7']] = df_final[['Path2', 'Path3', 'Path4', 'Path5','Path6', 'Path7']].replace(to_replace='', value=np.nan)
df_final.head()


## Fillup missing values in path with mode values
for features in ['Path2', 'Path3', 'Path4', 'Path5','Path6', 'Path7']:
    value = df_final[features].mode()[0]
    df_final[features].fillna(value, inplace=True)


values = df_final['Navigation_Difficulties'].mode()[0]
df_final['Navigation_Difficulties'].fillna(values, inplace=True)


## 
import plotly.express as px
import plotly.offline as pyo
pyo.init_notebook_mode()

fig = px.sunburst(df_final, path=['Path2', 'Path3', 'Path4', 'Path6', 'Path7'], 
                  values='Effort', color='Navigation_Difficulties', width=800, height=800,color_continuous_scale='RdBu',)

fig.update_layout(uniformtext=dict(minsize=18))
fig.show()


### pennsylvania and pittsburgh
df_pe_pi = df_final[df_final['urls'].str.contains('pennsylvania|pittsburgh')]


fig = px.sunburst(df_pe_pi, path=['Path2', 'Path3', 'Path4', 'Path6', 'Path7'], 
                  values='Searches', color='Navigation_Difficulties', width=860, height=860)

fig.update_layout(uniformtext=dict(minsize=18))
fig.show()


### DTV product
df_dtv = df_final[df_final['Product'] == 'DTV']


fig = px.sunburst(df_dtv, path=['Path2', 'Path3', 'Path4', 'Path6', 'Path7'], 
                  values='Searches', color='Navigation_Difficulties', width=860, height=860)

fig.update_layout(uniformtext=dict(minsize=18))
fig.show()

	count	mean	std	min	25%	50%	75%	max
Navigation_Difficulties
No	461.0	503.585683	580.211663	0.0	79.0	258.0	761.0	2192.0
Yes	541.0	486.053604	529.292070	0.0	102.0	270.0	699.0	2236.0

	count	mean	std	min	25%	50%	75%	max
TA
No	635.0	506.297638	549.749230	0.0	98.5	291.0	755.0	2236.0
Yes	367.0	473.049046	558.949197	0.0	75.0	244.0	668.5	2232.0

	count	mean	std	min	25%	50%	75%	max
Navigation_Difficulties
No	461.0	21.765291	13.471723	0.0	10.5	21.5	29.5	62.0
Yes	541.0	23.412598	13.014742	0.0	15.0	22.5	31.0	61.0

	count	mean	std	min	25%	50%	75%	max
TA
No	635.0	22.801183	13.417547	0.0	13.50	22.0	30.50	62.0
Yes	367.0	22.401263	12.957487	0.0	12.75	22.5	29.75	61.0

	count	mean	std	min	25%	50%	75%	max
Navigation_Difficulties
No	461.0	16.839479	14.746563	0.0	6.0	12.0	24.0	95.0
Yes	541.0	17.210721	15.548966	0.0	6.0	12.0	23.0	93.0

Navigation Difficiulties and TA when searches were not used¶

Navigation Difficiulties and TA when searches were used¶

Confusion Matrix for evaluation of model¶

Model perfomance when target feature is Reloads¶

Model perfomance when target feature is Product¶

Model perfomance when target feature is Platform¶

Model perfomance when target feature is Navigation Difficulties¶

Model perfomance when target feature is Navigation Difficulties¶

Forward Feature Selection¶

Things customers did before they clicked on seach¶

Number of Searches made by customers¶

Comparison of Navigation Difficiulties and Page URL¶

Comparison of Task accomplishment and Page URL¶

Sunburst Visualization¶

DTV Product¶

THE END

	foresee_respondent	foresee_session_id	wt_visitor_id	day	Survey_Category	Product	Platform	main_task	CSAT	TA	Effort	Navigation_Difficulties	Relevance	called_flag	app_session_id	event_count	page_loads	link_clicks	impressions	urls	Searches	Page Events	Page Views	Average Page Depth	Reloads	Time Spent per Visit (seconds)
0	axg6v1l5DA7iV2mItNiXZXIt1NwbFFzV	03aa8b78-4758-4fde-8260-10924007c86d	7.413472e+09	11/6/21	Account Management	DTV	App	Set up or manage Access ID/website profile (in...	66.67	No	5	Yes	7	1	45d04218-444f-434f-a9de-9542ec0ae70d	128.0	60.0	22.0	3.0	, /acctmgmt/fpwd/createnewpwd, /my/virtual/alr...	0.0	21.0	13.0	65.0	1.0	217.0
1	AxMp11NgEd5gUQQk5tZppQ4C	08ecdb46-47c4-4d40-bbbc-dbeee788e0f5	7.690689e+09	1/17/22	Account Management	Wireless	Desktop	Other	0.00	No	1	Yes	1	1	tghbavyJYORybfbQh-ciD72cBdYayZqTjztRRR9zQBM	39.0	11.0	14.0	9.0	/acctmgmt/accountoverview, /acctmgmt/wireless/...	NaN	NaN	NaN	NaN	NaN	NaN
2	c5odUJVxxMVBldAkEhdEIw4C	10d32120-8023-4720-8bdb-e63f57e99d65	6.756765e+09	12/12/21	Account Management	Other	Desktop	Add, change or downgrade plans and features (e...	0.00	No	1	Yes	1	0	mTkboOqXd6RjBQoDu0-1ahoiMsjVCpF4heKBmxb9UBE	19.0	3.0	3.0	5.0	/support/, /support/contact-us/	NaN	NaN	NaN	NaN	NaN	NaN
3	IMAyzf8pTFEiuRdoBZSPNnhnqEnzn5YP	208b4dd7-a0fd-40c3-b44e-84ff3be1f46b	7.570705e+09	1/14/22	Account Management	BB	App	Check usage	88.89	No	1	Yes	9	0	6ItGbcSYnePunpjfpKvx_CiPWNbInRq8nwj0O3shvPw	49.0	13.0	7.0	15.0	/virtual/nativemorenav, /acctmgmt/billandpay/h...	NaN	NaN	NaN	NaN	NaN	NaN
4	v7LSG4RWKj40pIUyRmIp3Z1BEb5FAo2k	290bf194-6762-44bd-8aad-8027a4f358c1	7.138217e+09	1/18/22	Account Management	Wireless	App	Make a payment	22.22	No	8	Yes	3	0	I0PFGM2HpNuk6fHTkrW_ayC7Qc76NM2fw7swz5j0U4k	15.0	7.0	2.0	2.0	/support/article/, /acctmgmt/makepayment/payme...	NaN	NaN	NaN	NaN	NaN	NaN

	0	1	2
8	Make a payment	None	None
25	Update payment method	None	None
62	Other	None	None
68	View current bill	None	None
75	Enroll	unenroll in AutoPay	None
79	Request a wireless device trade in or check th...	None	None
81	Make a payment arrangement	None	None
118	Make a payment	None	None
122	Troubleshooting - fix a problem with my device...	None	None
125	View previous bill(s)	None	None
145	View current bill	None	None
152	Make a payment	None	None
153	Other	None	None
157	Troubleshooting - fix a problem with my device...	None	None
169	Plan, features or service help - review, chang...	None	None
180	View current bill	None	None
183	Troubleshooting - fix a problem with my device...	None	None
196	Make a payment	None	None
240	View current bill	None	None
247	Billing, payment and usage help - pay, review ...	None	None
249	Other	None	None
307	Purchase, upgrade, check eligibility	None	None
308	Check usage	None	None
317	Other	None	None
356	Other	None	None
373	View current bill	None	None
396	Troubleshooting - fix a problem with my device...	None	None
404	View current bill	None	None
408	Troubleshooting - fix a problem with my device...	None	None
430	Learn how to use products, services or equipme...	None	None
447	Make a payment	None	None
460	Set up	activate products or services	None
464	Plan, features or service help - review, chang...	None	None
475	Plan, features or service help - review, chang...	None	None
482	Other	None	None
495	Other	None	None
514	Set up or manage Access ID	website profile (includes linking	unlinking accounts)
541	Update payment method	None	None
559	Other	None	None
568	View previous bill(s)	None	None
578	Other	None	None
581	Make a payment	None	None
594	Other	None	None
612	Make a payment	None	None
625	Check usage	None	None
629	Contact AT&T Customer Service	None	None
635	Set up or manage email account (includes email...	None	None
654	Set up or manage Access ID	website profile (includes linking	unlinking accounts)
663	Other	None	None
666	Account assistance - register new account, get...	None	None

	foresee_respondent	foresee_session_id	wt_visitor_id	day	Survey_Category	Product	Platform	main_task	CSAT	TA	Effort	Navigation_Difficulties	Relevance	called_flag	app_session_id	event_count	page_loads	link_clicks	impressions	urls	Searches	Page Events	Page Views	Average Page Depth	Reloads	Time Spent per Visit (seconds)
62	4VZ9cYkNlwJ1ZsJR5NQFlA4C	d00c7072-7405-45ef-931d-10a05e5e4cc6	7.383279e+09	11/16/21	Account Management	Wireless	Desktop	Other	0.00	No	3	Yes	1	0	J6oDR2EdRSrLWKKPdpk1OlyvBbDJPkNxho0yMP_WK28	39.0	10.0	18.0	6.0	/acctmgmt/billandpay, /acctmgmt/billandpay/his...	1.0	30.0	10.0	16.500000	1.0	425.0
68	AYMospUAEsAcw8URYlJxIg4C	facadf1d-cfb0-42cd-85aa-0dc8b95019e0	7.611786e+09	2/15/22	Account Management	BB	Desktop	View current bill	48.15	No	2	No	3	0	lQJTkB9owNWztujkvYBaRuEKdpzw6MvvtcK_kXcYTfo	20.0	5.0	3.0	4.0	/acctmgmt/accountoverview, /acctmgmt/billandpa...	1.0	16.0	7.0	3.000000	2.0	511.0
625	qNVhpw1EA0jnv2L792HC3E17Bhyg8tfo	d8ab5448-60c4-4c7d-9045-27a414f9b61c	7.724436e+09	2/1/22	Account Management	Wireless	Mobile Web	Check usage	44.44	Yes	3	Yes	4	0	fovtSFw2ZPH6qjAd2_bgsjzYfBxrOTP4eLXcAqe0omY	22.0	6.0	6.0	4.0	/acctmgmt/accountoverview, , /help/prepaid/, /...	1.0	14.0	6.0	4.500000	0.0	139.0
937	4hQdgIMtJootQxFEpRd50w4C	0e65c30e-88d3-4c7e-834a-71cdea355368	7.755826e+09	2/6/22	Account Management	Other services from AT&T (Home phone, DSL, etc.)	Desktop	Make a payment	0.00	No	1	Yes	1	0	6a7b614e-fbdd-493c-8f11-3552986a1c25	56.0	23.0	11.0	4.0	/acctmgmt/registration/welcome, /acctmgmt/acco...	1.0	12.0	3.0	38.000000	0.0	466.0
1100	F89cQ1QEkcVhdRA4lAMQFg4C	9a2aae94-e7d0-4580-84c6-5aa6c5c7b977	7.055668e+09	2/3/22	Account Management	Wireless	Desktop	Add, change or downgrade plans and features (e...	81.48	No	8	No	8	0	459ca1d2-8787-4cb3-ae19-d1d99877a316	27.0	9.0	7.0	3.0	/support/article/, /acctmgmt/wireless/device/o...	1.0	20.0	11.0	6.000000	0.0	1882.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
129062	VBN4ZUEt9xd991UpsMwZVQ4C	2ce2596e-8762-45b3-a4e7-d2e1571f41ad	6.856674e+09	12/9/21	Account Management	Wireless	Desktop	Request a wireless device trade in or check th...	14.81	No	5	Yes	5	0	Ziw5u6FN5RlLwTdM_rhd-NbLv8vbrdu0M89pE9mkX4Y	23.0	6.0	7.0	3.0	/acctmgmt/registration/welcome, /acctmgmt/regi...	1.0	33.0	16.0	7.500000	0.0	1147.0
133261	RdxhFQgY0JdppNx8c581Mg4C	85336e4c-9512-431c-9da2-da33d6d2787d	7.741791e+09	2/1/22	Support	BB	Desktop	Find out how to move my service(s) to a new ad...	0.00	No	1	Yes	2	0	gguCr9R8AY57um8yJMC1Mm5_PpL44Re7VkCxWmWBKjw	47.0	8.0	12.0	6.0	/buy/broadband/check-availability/modal, /shop...	1.0	35.0	15.0	8.000000	1.0	318.0
133993	QBihOgjCDynWdJ4UykIQNX9gSv304HeZ	4a291b4b-cff1-4f04-a445-9dc0c4b6c7b0	7.613172e+09	12/1/21	Account Management	Wireless	Mobile Web	View current bill	100.00	Yes	10	No	10	0	v9HwIhSGqRbz6A-DE6eFF04E3kuFKtwZfMahkfWm6-o	22.0	5.0	3.0	8.0	, /features/myatt-app/, /, /my/virtual/viewbil...	1.0	21.0	9.0	4.000000	2.0	416.0
134043	lV8YlFBV1Rg5gMchVZAtNw4C	f59d92d5-15f8-4510-be23-6a47a63dfa7d	7.615036e+09	12/23/21	Support	DTV	Desktop	Contact AT&T Customer Service - find phone num...	0.00	No	1	No	1	0	8rOWe7OuIx5QmKCZ1Q4Od-bOIx_tYd3RJpfGX0f2Cu0	50.0	14.0	10.0	13.0	/help/cancellation-policy/, , /acctmgmt/accoun...	1.0	5.0	2.0	15.500000	0.0	722.0
135124	dNpVINcMtlgRIFsJYot9pw4C	df3da0a6-cff4-4943-af7c-79c3d3c7c241	6.846253e+09	11/4/21	Account Management	Wireless	Desktop	Check order status	0.00	No	1	No	1	0	MldXfEft5673fopgmjVtooJG7yJ--RBHyztaQNBRMzU	63.0	12.0	23.0	13.0	/acctmgmt/wireless/device/optionsettings, /sup...	1.0	19.0	12.0	27.916667	1.0	483.0

	Missing Values
Product	0
Platform	0
Reloads	0
Average Page Depth	0
Page Views	0
Page Events	0
Searches	0
impressions	0
link_clicks	0
page_loads	0
event_count	0
called_flag	0
Relevance	0
Navigation_Difficulties	0
Effort	0
TA	0
CSAT	0
Time Spent per Visit (seconds)	0

	TA
62	No
153	No
249	No
317	Yes
356	No
...	...
135446	Yes
135452	No
135822	Yes
135826	Yes
136012	No

	count	mean	std	min	25%	50%	75%	max
Navigation_Difficulties
No	461.0	7.255965	6.234511	1.0	2.0	5.0	10.0	35.0
Yes	541.0	7.314233	6.166604	1.0	3.0	6.0	10.0	34.0

	count	mean	std	min	25%	50%	75%	max
Survey_Category
Account Management	699.0	11.125894	6.499606	0.0	6.0	10.0	16.0	29.0
Support	303.0	10.990099	6.097706	1.0	6.0	10.0	15.0	29.0

	count	mean	std	min	25%	50%	75%	max
Platform
App	295.0	280.969492	353.429682	0.0	56.5	145.0	344.00	2016.0
Desktop	510.0	615.986275	606.431672	0.0	127.0	405.0	943.75	2221.0
Mobile Web	197.0	497.812183	559.341103	0.0	89.0	262.0	737.00	2236.0

	count	mean	std	min	25%	50%	75%	max
Platform
App	295.0	10.728814	6.305786	2.0	5.0	10.0	15.0	29.0
Desktop	510.0	11.274510	6.426793	1.0	6.0	11.0	15.0	29.0
Mobile Web	197.0	11.126904	6.368700	0.0	6.0	11.0	15.0	29.0

	count	mean	std	min	25%	50%	75%	max
Platform
App	295.0	17.711864	16.727763	0.0	6.0	12.0	23.5	93.0
Desktop	510.0	17.656863	14.697002	0.0	7.0	13.0	25.0	95.0
Mobile Web	197.0	14.436548	13.692776	0.0	5.0	10.0	19.0	70.0

	APP_SESSION_ID	FORESEE_SESSION	ERROR_CODES
0	c222a3fb-c62d-4710-ad66-49b2580ba9d1	9d314b30-9abf-4e77-9b3e-1257b823b88d	REG_BE_200,REG_BV_002
1	g0m8IoKwE8gPtVA7VnuIHdVYBifI6crJCST3e4iI1Dc	24e04221-cf77-432e-84b6-b62311051f68	PFS10006,201,MS_ORCH_FID_LE_BE_01_OK
2	_z0RK7lnruN9USCJuu7J3WJ0zCGCM4D9g0LKCu6peU4	e98ffd19-2b5d-434f-9dc6-9d06d4374328	PMS10002,PMS10010,-2
3	ZLKJSx4fSoFlDMcMzfsChpIPVM18GZmAugzmNiHV1l0	3362eee1-62cd-4506-803c-3e22a43a495f	-2,MSPMT_E200101,1
4	917nZt30odWeiH5XORj_aWE9LWn-LHlyhmIwmBVRS6k	5e73673a-7df1-48de-a261-209404f9c499	1,LGN_02_07

	foresee_respondent	foresee_session_id	wt_visitor_id	day	Survey_Category	Product	Platform	main_task	TA	Effort	Navigation_Difficulties	Relevance	app_session_id	event_count	page_loads	link_clicks	impressions	urls	Searches	Page Events	Page Views	Average Page Depth	Reloads	Time Spent per Visit (seconds)	FORESEE_SESSION	APP_SESSION_ID	EVENT_DATE	EVENT_DATETIME	PAGE_URL	PAGE_GROUP	EVENT_CODE	R	Path2	Path3	Path4	Path5	Path6	Path7
64	oJNB91QlQUVsMgtst18Vcw4C	2115de72-a3ce-4aaf-b08f-d3aa476e6024	7.679903e+09	1/5/22	Account Management	Wireless	Desktop	View previous bill(s)	No	2	Yes	2	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	60.0	19.0	17.0	9.0	/support/contact-us/, /wireless/, , /acctmgmt/...	6.0	16.0	5.0	26.0	2.0	1055.0	2115de72-a3ce-4aaf-b08f-d3aa476e6024	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	05/01/2022	18:36.0	/wireless/	SALES (Not Product-Specific)	Link_Click	1	wireless	NaN	NaN	NaN	search,	u-verse-voice
65	oJNB91QlQUVsMgtst18Vcw4C	2115de72-a3ce-4aaf-b08f-d3aa476e6024	7.679903e+09	1/5/22	Account Management	Wireless	Desktop	View previous bill(s)	No	2	Yes	2	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	60.0	19.0	17.0	9.0	/support/contact-us/, /wireless/, , /acctmgmt/...	6.0	16.0	5.0	26.0	2.0	1055.0	2115de72-a3ce-4aaf-b08f-d3aa476e6024	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	05/01/2022	18:45.0	/wireless/	SALES (Not Product-Specific)	Link_Click	2	wireless	NaN	NaN	NaN	search,	u-verse-voice
66	oJNB91QlQUVsMgtst18Vcw4C	2115de72-a3ce-4aaf-b08f-d3aa476e6024	7.679903e+09	1/5/22	Account Management	Wireless	Desktop	View previous bill(s)	No	2	Yes	2	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	60.0	19.0	17.0	9.0	/support/contact-us/, /wireless/, , /acctmgmt/...	6.0	16.0	5.0	26.0	2.0	1055.0	2115de72-a3ce-4aaf-b08f-d3aa476e6024	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	05/01/2022	26:32.0	/acctmgmt/billandpay	ONLINE CARE (Not Product-Specific)	Page_Load	3	acctmgmt	billandpay	NaN	NaN	search,	u-verse-voice
67	oJNB91QlQUVsMgtst18Vcw4C	2115de72-a3ce-4aaf-b08f-d3aa476e6024	7.679903e+09	1/5/22	Account Management	Wireless	Desktop	View previous bill(s)	No	2	Yes	2	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	60.0	19.0	17.0	9.0	/support/contact-us/, /wireless/, , /acctmgmt/...	6.0	16.0	5.0	26.0	2.0	1055.0	2115de72-a3ce-4aaf-b08f-d3aa476e6024	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	05/01/2022	26:37.0	/acctmgmt/billandpay/history	ONLINE CARE (Not Product-Specific)	Page_Load	4	acctmgmt	billandpay	history	NaN	search,	u-verse-voice
68	oJNB91QlQUVsMgtst18Vcw4C	2115de72-a3ce-4aaf-b08f-d3aa476e6024	7.679903e+09	1/5/22	Account Management	Wireless	Desktop	View previous bill(s)	No	2	Yes	2	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	60.0	19.0	17.0	9.0	/support/contact-us/, /wireless/, , /acctmgmt/...	6.0	16.0	5.0	26.0	2.0	1055.0	2115de72-a3ce-4aaf-b08f-d3aa476e6024	fe1YBsBbQrwETnEZCltkd2o2HBFXLuUFz_IoLZYH_58	05/01/2022	26:41.0	/acctmgmt/atvbillpayments	ONLINE CARE (Not Product-Specific)	Page_Load	5	acctmgmt	atvbillpayments	NaN	NaN	search,	u-verse-voice

	count	mean	std	min	25%	50%	75%	max
Platform
App	295.0	31.458975	12.634395	1.0	23.75	31.0	38.233333	62.0
Desktop	510.0	18.527578	11.643690	0.0	8.50	18.0	25.000000	57.5
Mobile Web	197.0	20.155089	11.715889	1.0	11.00	20.5	26.000000	61.0

	count	mean	std	min	25%	50%	75%	max
Platform
App	295.0	0.837288	1.160855	0.0	0.0	0.0	1.0	5.0
Desktop	510.0	0.784314	1.166219	0.0	0.0	0.0	1.0	5.0
Mobile Web	197.0	0.730964	1.031991	0.0	0.0	0.0	1.0	5.0

	foresee_session	search_terms
0	0048f7c6-870d-4929-9585-c15d817bd4a3	where can i find the password for my router
1	007e2653-07cc-43b4-af52-b1fbd695c7df	i do not have auto pay and some one debited ...
2	0089b782-3aad-4294-aef4-bda8957615c5	recycle equipment
3	0094f7bf-0c6b-4e9c-96bc-4f877c36d662	internet security suite download, internet ...
4	00ad6f19-4e16-4515-8bb7-f3d3fcfafb80	att sent me a text saying that you are givin...

	APP_SESSION_ID	FORESEE_SESSION	ERROR_CODES	foresee_session	search_terms	foresee_respondent	foresee_session_id	wt_visitor_id	day	Survey_Category	Product	Platform	main_task	CSAT	TA	Effort	Navigation_Difficulties	Relevance	app_session_id	event_count	page_loads	link_clicks	impressions	urls	Searches	Page Events	Page Views	Average Page Depth	Reloads	Time Spent per Visit (seconds)	Search
0	jL9BaVnPvstmKC1wZVmcS8AgY00ewZlWiPXHKLElTa4	1906c7ac-8998-47d3-b2e3-e3dec83a6965	0,-2	1906c7ac-8998-47d3-b2e3-e3dec83a6965	appointment	ktSsvYnsVJzZkAq3KuvfDhRfgrle9N0e	1906c7ac-8998-47d3-b2e3-e3dec83a6965	7.722781e+09	1/30/22	Support	BB	Mobile Web	Other	0.00	No	1	Yes	1	jL9BaVnPvstmKC1wZVmcS8AgY00ewZlWiPXHKLElTa4	36.0	11.0	5.0	4.0	/acctmgmt/accountoverview, /search, /support/a...	0.0	2.0	1.0	15.000000	0.0	830.0	Didn't use search
1	HzlpveI8jY02EbaRBW7gK6Z29KvwdC2PnxgTeeBka6E	bb8e44e7-fee1-42ca-b629-b272364e1cd5	0,1	bb8e44e7-fee1-42ca-b629-b272364e1cd5	signature program enrollment, fan 5339885	O5b6UHUsmuefVSGXNYZniWfYP6HB02yu	bb8e44e7-fee1-42ca-b629-b272364e1cd5	7.366163e+09	1/7/22	Account Management	Wireless	App	Other	40.74	No	2	Yes	2	HzlpveI8jY02EbaRBW7gK6Z29KvwdC2PnxgTeeBka6E	30.0	9.0	3.0	5.0	/my/virtual/accountoverview, /verification/sig...	0.0	65.0	21.0	38.000000	0.0	428.0	Didn't use search
2	zPHphjHODqTvcVY6ZCr2bLRH3CrgSNX1y8Ud92QzSkc	5a8f4cdc-bd9a-41db-aaea-35e5256b2885	-2	5a8f4cdc-bd9a-41db-aaea-35e5256b2885	discount	s4QUwN5khglNo9cExAcZxQ4C	5a8f4cdc-bd9a-41db-aaea-35e5256b2885	6.602690e+09	1/25/22	Account Management	Wireless	Desktop	Other	0.00	No	1	Yes	1	zPHphjHODqTvcVY6ZCr2bLRH3CrgSNX1y8Ud92QzSkc	45.0	12.0	12.0	4.0	/acctmgmt/tobr/transfersummary, /verification/...	0.0	10.0	3.0	18.000000	0.0	177.0	Didn't use search
3	o398yfrcnWmqcfbyWFzQlt-vndv1pKXMBCqweEcAEBo	6c085f25-90c4-45a3-ae83-61bb8276e5df	205.4,205.2,MSFIDACL08,MSFIDELAG00	6c085f25-90c4-45a3-ae83-61bb8276e5df	email login	ZgpsJJ4ARx98goU0VIV1Rw4C	6c085f25-90c4-45a3-ae83-61bb8276e5df	6.865271e+09	1/22/22	Support	BB	Desktop	Other	0.00	No	1	Yes	1	o398yfrcnWmqcfbyWFzQlt-vndv1pKXMBCqweEcAEBo	32.0	5.0	2.0	2.0	/search, , /acctmgmt/fid/emailaccount, /acctmg...	0.0	15.0	13.0	55.692308	1.0	1605.0	Didn't use search
4	fM-dl2aLtzdeJGhecUsSXwb1VZBrbLx07qsVLZ0fyL8	07d09594-21a1-4490-9f16-6694053a1eb6	0	07d09594-21a1-4490-9f16-6694053a1eb6	how do i print my statement	3594e2gPZLuuTOY3dJ3hYI78VfIP81Y8	07d09594-21a1-4490-9f16-6694053a1eb6	6.445448e+09	1/18/22	Account Management	Wireless	App	Other	0.00	No	1	No	1	fM-dl2aLtzdeJGhecUsSXwb1VZBrbLx07qsVLZ0fyL8	21.0	5.0	3.0	6.0	/search, , /acctmgmt/billandpay, /support/topi...	0.0	82.0	18.0	27.500000	1.0	762.0	Didn't use search
5	E-6xuKM1nbXOp_fMldltQKEXUGzrVvLS1mUB929yfhk	ed04f7f0-ff55-4493-ba21-199c094143d6	-2	ed04f7f0-ff55-4493-ba21-199c094143d6	connectivity program, connectivity program	BNpSJFtw6ehmqwzBV4QEMOv4asd1mYC6	ed04f7f0-ff55-4493-ba21-199c094143d6	7.783611e+09	2/18/22	Support	Wireless	Mobile Web	Other	22.22	Yes	1	Yes	3	E-6xuKM1nbXOp_fMldltQKEXUGzrVvLS1mUB929yfhk	37.0	11.0	10.0	9.0	/acctmgmt/accountoverview, /help/affordable-co...	0.0	6.0	3.0	26.000000	0.0	30.0	Didn't use search
6	UP19i0Ypn-zxk2HsOPDfhzS4gGjS2jY-dFX7iid7a5E	b0bf9b86-faca-4609-bdf6-edf9659f9875	201,-2	b0bf9b86-faca-4609-bdf6-edf9659f9875	reward card	EhYRJ158VYYpRI00EVY8RA4C	b0bf9b86-faca-4609-bdf6-edf9659f9875	7.698561e+09	1/16/22	Account Management	BB	Desktop	Other	88.89	Yes	10	No	10	UP19i0Ypn-zxk2HsOPDfhzS4gGjS2jY-dFX7iid7a5E	16.0	5.0	3.0	2.0	/search, , /myfavorites, /my/virtual/verifyema...	0.0	24.0	14.0	7.500000	1.0	1142.0	Didn't use search
7	3VrbsgEz4boyORWbh9b5ReUKOnXJa7DOKPZWpAKuWzs	ccd008d5-ad91-481d-af17-453072004f86	0,LGN_02_07,-2	ccd008d5-ad91-481d-af17-453072004f86	feedback, feedback, complaints, feedback,...	NbXigqh82nmJX2KVgPKxZ76G5dNKGr1g	ccd008d5-ad91-481d-af17-453072004f86	7.702964e+09	1/18/22	Account Management	Wireless	Mobile Web	Other	0.00	No	1	No	1	3VrbsgEz4boyORWbh9b5ReUKOnXJa7DOKPZWpAKuWzs	90.0	26.0	17.0	10.0	/acctmgmt/fpwd/selectmethod, /acctmgmt/fpwd/re...	4.0	21.0	8.0	45.500000	2.0	149.0	Used Search
8	I-tIoLOPqfuCmAc5qCFv6-tMcvOAWT-xpSRVQdXgduY	02803df1-5eb1-4608-bd94-58dc7bc28128	-2,1,201	02803df1-5eb1-4608-bd94-58dc7bc28128	unlock phone	zVV7pXpwnNRh0kLY4FBMu1tBg5aPZQ9Z	02803df1-5eb1-4608-bd94-58dc7bc28128	7.704693e+09	1/21/22	Account Management	Wireless	Mobile Web	Other	77.78	Yes	5	No	8	I-tIoLOPqfuCmAc5qCFv6-tMcvOAWT-xpSRVQdXgduY	65.0	20.0	14.0	9.0	/deviceunlock/unlockstep2, /deviceunlock/unloc...	0.0	3.0	4.0	33.500000	0.0	155.0	Didn't use search
9	cMAfnuFfxIjFfTHj1En3Na2JdyeV2v3jeogTufcz6FI	f07cb7de-484e-4d87-8568-bd51d9d78653	0,-2	f07cb7de-484e-4d87-8568-bd51d9d78653	i wanna change my wi-fi password, i wanna c...	7gB8G8bxzPnjW93tCZE8seksISZDvrdA	f07cb7de-484e-4d87-8568-bd51d9d78653	7.751387e+09	2/3/22	Support	BB	Mobile Web	Other	0.00	No	1	Yes	1	cMAfnuFfxIjFfTHj1En3Na2JdyeV2v3jeogTufcz6FI	73.0	18.0	10.0	14.0	/buy/phones, /, /buy/cart, /support/contact-us...	0.0	70.0	19.0	22.000000	2.0	980.0	Didn't use search
10	_T4kw6QzgvNiBxFMBC7z8tsQ79YgDdmfUtfRVrpTnuc	791dea66-a9b2-438a-a290-2a05569156bc	1	791dea66-a9b2-438a-a290-2a05569156bc	contact information, contact information, ...	Q9IptUUENQc8sNEt8xwIYw4C	791dea66-a9b2-438a-a290-2a05569156bc	7.625703e+09	1/17/22	Support	Wireless	Desktop	Other	0.00	No	5	Yes	1	_T4kw6QzgvNiBxFMBC7z8tsQ79YgDdmfUtfRVrpTnuc	71.0	13.0	16.0	12.0	/acctmgmt/accountoverview, /support/topic/my-a...	3.0	19.0	6.0	17.500000	2.0	946.0	Used Search
11	83b804ad-6e79-4e07-ace6-a25e44b92fe9	80877da0-92a3-488d-86bf-849ed5c32ac4	-2,1	80877da0-92a3-488d-86bf-849ed5c32ac4	unlimi	SWfVQxtl8cLm9ZfSsWgyPJO2bdboYjTZ	80877da0-92a3-488d-86bf-849ed5c32ac4	7.795247e+09	2/20/22	Support	Wireless	Mobile Web	Other	96.30	Yes	5	No	9	83b804ad-6e79-4e07-ace6-a25e44b92fe9	74.0	26.0	14.0	14.0	/support/article/, /acctmgmt/wireless/device/d...	0.0	23.0	11.0	26.000000	2.0	353.0	Didn't use search
12	_tPuRpH78pcP09ZP26I-2SkvU3HqkV_VsPqzQyRlh8M	d1773bca-bc5d-4491-a4e9-79ba1d4828f9	-2,1	d1773bca-bc5d-4491-a4e9-79ba1d4828f9	employee and retiree discount	4ohx98RxoAwQoNxo8dV95A4C	d1773bca-bc5d-4491-a4e9-79ba1d4828f9	5.509732e+09	2/12/22	Account Management	Wireless	Desktop	Other	62.96	Yes	6	Yes	7	_tPuRpH78pcP09ZP26I-2SkvU3HqkV_VsPqzQyRlh8M	56.0	12.0	5.0	9.0	/acctmgmt/accountoverview, /acctmgmt/registrat...	0.0	16.0	6.0	6.666667	2.0	0.0	Didn't use search
13	2333560d-298e-4818-b7ac-9236cb833126	11e5f7e0-d9a6-4aff-9f63-e2ae7bdab222	0,-2	11e5f7e0-d9a6-4aff-9f63-e2ae7bdab222	receive free at&t cell booster because of up...	cEyH7o69Xvu49ImoxoC2bzSDoNi5OGt7	11e5f7e0-d9a6-4aff-9f63-e2ae7bdab222	7.784615e+09	2/14/22	Support	Wireless	Mobile Web	Other	0.00	No	2	Yes	1	2333560d-298e-4818-b7ac-9236cb833126	73.0	10.0	1.0	12.0	/support/article/, /support/, /search, /Accept...	0.0	30.0	10.0	28.500000	1.0	392.0	Didn't use search
14	2761eb41-90e2-45b7-b2a6-a6ab5f5b9973	ab023c8d-26f5-4a4a-a7fb-0888ed06d5c1	205.4	ab023c8d-26f5-4a4a-a7fb-0888ed06d5c1	anti virus	lpQ599xZ4sEckYwksMstMA4C	ab023c8d-26f5-4a4a-a7fb-0888ed06d5c1	7.759407e+09	2/8/22	Support	BB	Desktop	Other	0.00	No	1	Yes	1	2761eb41-90e2-45b7-b2a6-a6ab5f5b9973	37.0	9.0	6.0	14.0	/acctmgmt/registration/serviceselection, /supp...	0.0	20.0	9.0	34.555556	1.0	128.0	Didn't use search
15	cv_AW5zy7vDpK0N-WbGD6mYWe8yeJ-fVCHiHfpd9wjU	f4318982-e731-48a3-8b79-18bdde01431c	0	f4318982-e731-48a3-8b79-18bdde01431c	report text spam	pEcrUJKOe3JDUyrjcrDH4U0VPnn3XI1g	f4318982-e731-48a3-8b79-18bdde01431c	7.177417e+09	1/11/22	Support	Wireless	App	Other	100.00	Yes	9	No	10	cv_AW5zy7vDpK0N-WbGD6mYWe8yeJ-fVCHiHfpd9wjU	27.0	9.0	3.0	3.0	/support/article/, , /myatt/index-native.html,...	0.0	5.0	2.0	38.500000	0.0	123.0	Didn't use search
16	dffd3255-a5cc-4836-b41c-9e0bbca4b9a7	d8083682-4e02-4339-ab63-6f2afb989e98	1,-2	d8083682-4e02-4339-ab63-6f2afb989e98	how to get passcode for smart home manager	Z3AMLQdh9WFv9wq2W3kjvSHLkVRxX8Ot	d8083682-4e02-4339-ab63-6f2afb989e98	7.685185e+09	1/9/22	Support	BB	Mobile Web	Other	100.00	No	10	Yes	5	dffd3255-a5cc-4836-b41c-9e0bbca4b9a7	47.0	7.0	9.0	8.0	/internet/smart-home/, /acctmgmt/accountovervi...	0.0	14.0	7.0	14.000000	0.0	1232.0	Didn't use search
17	UBGgxIHqLQ7UsBS4Png4SBSQE43dgj5FL3lli37DiC4	5b2d10c4-4176-4a11-a9cb-e307e4b3b764	0,201,1	5b2d10c4-4176-4a11-a9cb-e307e4b3b764	transfer number to another carrier, unlock	lF9xt8IYF0MgwAsYB05ddw4C	5b2d10c4-4176-4a11-a9cb-e307e4b3b764	7.671234e+09	1/1/22	Account Management	Wireless	Desktop	Other	74.07	Yes	4	No	6	UBGgxIHqLQ7UsBS4Png4SBSQE43dgj5FL3lli37DiC4	36.0	13.0	3.0	5.0	/deviceunlock/thankyou, /deviceunlock/unlockst...	0.0	23.0	13.0	11.000000	1.0	608.0	Didn't use search
18	PMs-aWqwFXHOKlLXV19HesSJv4o7LmpMnlAet4Z5dWA	5e9589fa-2a08-49f6-a34e-cef2de2e0f5e	902,201,-2,1	5e9589fa-2a08-49f6-a34e-cef2de2e0f5e	microcell	osg5cAVEZlY4IJNRg9lNog4C	5e9589fa-2a08-49f6-a34e-cef2de2e0f5e	7.777070e+09	2/14/22	Support	Wireless	Desktop	Other	0.00	No	10	Yes	1	PMs-aWqwFXHOKlLXV19HesSJv4o7LmpMnlAet4Z5dWA	64.0	11.0	13.0	12.0	/search, /acctmgmt/accountoverview, /support/,...	0.0	13.0	3.0	28.000000	2.0	588.0	Didn't use search
19	QjYiFC3jKCcXS6ZoDSaCUiQQq9yrGckXxm-0jsGyPi8	921b5dc2-fc76-4752-a3ee-d9c42f4bb7cd	902,205.4,-2	921b5dc2-fc76-4752-a3ee-d9c42f4bb7cd	security suite download	dkJIAIYYkwBcMUQpE9IAgw4C	921b5dc2-fc76-4752-a3ee-d9c42f4bb7cd	7.699021e+09	1/16/22	Support	BB	Desktop	Other	0.00	No	1	Yes	1	QjYiFC3jKCcXS6ZoDSaCUiQQq9yrGckXxm-0jsGyPi8	41.0	12.0	7.0	8.0	/search, , /support/article/, /, /internet/fib...	1.0	10.0	2.0	43.000000	1.0	668.0	Used Search
20	00rGvGm8YUxMOpP5otOR3J_9SarR7h7oCmLzvqbBFwA	6ea46be0-9109-4714-a3e0-8e585482e943	0,1,201,-2	6ea46be0-9109-4714-a3e0-8e585482e943	suspend	9hwc1pENNNAAYsgc40QQRw4C	6ea46be0-9109-4714-a3e0-8e585482e943	6.916094e+09	1/31/22	Support	Wireless	Desktop	Other	85.19	Yes	8	No	7	00rGvGm8YUxMOpP5otOR3J_9SarR7h7oCmLzvqbBFwA	68.0	17.0	14.0	8.0	, /support/smallbusiness/article/change-device...	0.0	13.0	5.0	18.000000	0.0	993.0	Didn't use search
21	1l1kNzw_sEzrMJXBzx7bXLke44PI_Ohd0HUDMlg4LxA	8be56008-2d38-4a37-884b-54310af79033	1,-2	8be56008-2d38-4a37-884b-54310af79033	international	MNodhYcNAtZ8coUd1BgMtQ4C	8be56008-2d38-4a37-884b-54310af79033	7.671885e+09	1/1/22	Account Management	Wireless	Desktop	Other	77.78	Yes	8	No	7	1l1kNzw_sEzrMJXBzx7bXLke44PI_Ohd0HUDMlg4LxA	36.0	12.0	11.0	4.0	/international/day-pass/, /acctmgmt/wireless/d...	4.0	26.0	15.0	8.000000	1.0	1414.0	Used Search
22	n3G5vbxNCES_TJGB4k-UCaxJ6jTO-lJ6hDtUr3yaW_k	0e98288d-227b-4722-ab70-faa2b2766c7d	-2	0e98288d-227b-4722-ab70-faa2b2766c7d	chat	2LjGjDtB4ZJp1YnOsdBlPrA73U0H01Gv	0e98288d-227b-4722-ab70-faa2b2766c7d	7.786353e+09	2/16/22	Account Management	Wireless	Mobile Web	Other	44.44	No	5	No	3	n3G5vbxNCES_TJGB4k-UCaxJ6jTO-lJ6hDtUr3yaW_k	38.0	10.0	5.0	7.0	/acctmgmt/makepayment, /acctmgmt/billandpay/hi...	0.0	11.0	5.0	17.000000	2.0	875.0	Didn't use search
23	-tgPaLs2YjGV23uoZ4jw2_SEQjstr4PLF8r65A7K_G4	2aae6e7d-77ee-4be9-ab6f-1ef7aea637e3	902,0	2aae6e7d-77ee-4be9-ab6f-1ef7aea637e3	mcell replacement, mcell replacement, mcel...	s9IBwMwxEAI9Btpg0F8N1g4C	2aae6e7d-77ee-4be9-ab6f-1ef7aea637e3	7.754894e+09	2/5/22	Support	Wireless	Desktop	Other	37.04	No	8	Yes	6	#NAME?	51.0	11.0	7.0	11.0	/checkmyorder/omhub.rt, /haloc/virtual/login/e...	0.0	6.0	5.0	9.800000	0.0	939.0	Didn't use search
24	pMuJTC87rmF-ss0YhU4K00JIa6VPYmdsD7F5sW1UyS4	f720b92f-124a-4bcd-815b-7be035e2df55	-2,1	f720b92f-124a-4bcd-815b-7be035e2df55	att fiber	YgcZQlxZRxgh4JIkl4wZEw4C	f720b92f-124a-4bcd-815b-7be035e2df55	7.531885e+09	1/26/22	Support	BB	Desktop	Other	29.63	No	5	Yes	5	pMuJTC87rmF-ss0YhU4K00JIa6VPYmdsD7F5sW1UyS4	59.0	17.0	10.0	15.0	/search, /buy/broadband/existing-service/modal...	0.0	49.0	34.0	52.029412	4.0	1731.0	Didn't use search
25	4f73c455-d669-47ea-abb4-497426b5f7cb	59e1e72c-f113-4db4-8fff-96b9a622d616	-2,0,ERR0003	59e1e72c-f113-4db4-8fff-96b9a622d616	track technician	Oq8vp5QUsrShT0DQKizjK0kE0suyGqLh	59e1e72c-f113-4db4-8fff-96b9a622d616	7.798002e+09	2/21/22	Support	BB	Mobile Web	Other	51.85	No	3	Yes	4	4f73c455-d669-47ea-abb4-497426b5f7cb	45.0	12.0	3.0	10.0	/tsrhs/virtual/smartphone/preflow/welcometotro...	0.0	11.0	2.0	19.500000	0.0	115.0	Didn't use search
26	2e033f96-c8b2-49be-afbf-c7fb386ad0f6	b50b7e65-ff77-4a0e-973f-c2746eda04d9	1,-2	b50b7e65-ff77-4a0e-973f-c2746eda04d9	voice mail	No4cw11JV5hZYBd9hs48Ig4C	b50b7e65-ff77-4a0e-973f-c2746eda04d9	7.780587e+09	2/11/22	Account Management	Wireless	Desktop	Other	88.89	Yes	7	No	9	2e033f96-c8b2-49be-afbf-c7fb386ad0f6	68.0	15.0	20.0	13.0	/support/article/, , /my/virtual/contactinfo, ...	0.0	7.0	3.0	18.000000	0.0	696.0	Didn't use search
27	-p4MuMP4ln6lfeiGrfBRWjvT1LxItz0oBLTFHasQUJk	42c605eb-bbec-4778-a46e-f37afff76c36	-2,201	42c605eb-bbec-4778-a46e-f37afff76c36	technical support	SVgn6udhpqgBxAMNC3utqM2xYenTXdN7	42c605eb-bbec-4778-a46e-f37afff76c36	7.680895e+09	1/12/22	Support	Wireless	Mobile Web	Other	0.00	No	1	No	1	#NAME?	60.0	9.0	9.0	7.0	/search, , /support/ts/wireless/phonecalls, /d...	0.0	6.0	1.0	11.000000	0.0	15.0	Didn't use search
28	J4rcrzGtv9dL4iLsuRpou0xg3PYJcmsHiDf3OAsSL1c	f3d5447f-9b91-4369-ae3d-6a2e21b8dcd6	0	f3d5447f-9b91-4369-ae3d-6a2e21b8dcd6	why does my bill keep getting higher	mVQUU3Q4TyWGF4cMKINI218SAXwxLpio	f3d5447f-9b91-4369-ae3d-6a2e21b8dcd6	5.611405e+09	2/10/22	Account Management	Wireless	App	Other	40.74	No	4	Yes	4	J4rcrzGtv9dL4iLsuRpou0xg3PYJcmsHiDf3OAsSL1c	108.0	22.0	16.0	11.0	/search, /acctmgmt/error, /, /support/topic/my...	0.0	57.0	2.0	27.500000	0.0	283.0	Didn't use search
29	pWO7zeo9GvOy0tLulWgXAE8KhTykpk3GJKsfGVP6Je8	c347b144-4632-462a-b1f0-dafd5c5469e9	1,-2	c347b144-4632-462a-b1f0-dafd5c5469e9	transfer phone pin, transfer to different c...	1NJNIhpkIl5sQQB9QUk04g4C	c347b144-4632-462a-b1f0-dafd5c5469e9	7.716904e+09	1/26/22	Account Management	Wireless	Desktop	Other	66.67	No	2	Yes	5	pWO7zeo9GvOy0tLulWgXAE8KhTykpk3GJKsfGVP6Je8	75.0	20.0	17.0	13.0	/acctmgmt/registration/confirmation, /acctmgmt...	0.0	29.0	8.0	21.500000	0.0	397.0	Didn't use search
30	GdzmzDC5wPCNAR7wpyXb3-V7gdjbB2ZmmfaK-lneDRQ	cd52db5e-a581-4950-9e84-8ddcd1353549	1,201,0,-2	cd52db5e-a581-4950-9e84-8ddcd1353549	why isn't my mobile phone connected to internet	8cVIJ01Zc1khw5dxg8x8RQ4C	cd52db5e-a581-4950-9e84-8ddcd1353549	7.505438e+09	1/11/22	Support	BB	Desktop	Other	33.33	No	1	Yes	1	GdzmzDC5wPCNAR7wpyXb3-V7gdjbB2ZmmfaK-lneDRQ	73.0	15.0	23.0	15.0	/support/, /search, /support/topic/u-verse-hig...	0.0	2.0	1.0	23.000000	0.0	1466.0	Didn't use search
31	SvNDLOpvseJJbQECWCyVtR-6CVh8UO48xOkKSEoUT6s	0582e189-b3c4-4fc0-b8bf-25b904d24444	-2,1	0582e189-b3c4-4fc0-b8bf-25b904d24444	direct tv discount	wtMosdoog19sVAQlNUAZJQ4C	0582e189-b3c4-4fc0-b8bf-25b904d24444	7.684402e+09	1/12/22	Account Management	Wireless	Desktop	Other	85.19	Yes	8	No	7	SvNDLOpvseJJbQECWCyVtR-6CVh8UO48xOkKSEoUT6s	68.0	20.0	9.0	10.0	, /my/virtual/attcomm, /bundles/, /buy/postpai...	0.0	3.0	1.0	23.000000	0.0	68.0	Didn't use search

	foresee_respondent	foresee_session_id	wt_visitor_id	day	Survey_Category	Product	Platform	main_task	CSAT	TA	Effort	Navigation_Difficulties	Relevance	called_flag	app_session_id	event_count	page_loads	link_clicks	impressions	urls	Searches	Page Events	Page Views	Average Page Depth	Reloads	Time Spent per Visit (seconds)	FORESEE_SESSION	APP_SESSION_ID	EVENT_DATE	EVENT_DATETIME	PAGE_URL	PAGE_GROUP	EVENT_CODE	R
0	GUhYhGecMg3xfNbf0mJ9j97Dybjj2Lto	019bab3a-e4fc-48e8-b54a-d3c241aa8465	7.418337e+09	11/26/21	Support	Wireless	Mobile Web	Troubleshooting - fix a problem with my device...	0.0	No	1	No	1	0	98674899-e129-492a-8d86-2c2af6024a82	46.0	13.0	13.0	10.0	/support/topic/wireless, /buy/phones/details, ...	0.0	7.0	2.0	17.5	0.0	295.0	019bab3a-e4fc-48e8-b54a-d3c241aa8465	98674899-e129-492a-8d86-2c2af6024a82	26/11/2021	38:56.6	/support/	NaN	Link_Click	1
1	GUhYhGecMg3xfNbf0mJ9j97Dybjj2Lto	019bab3a-e4fc-48e8-b54a-d3c241aa8465	7.418337e+09	11/26/21	Support	Wireless	Mobile Web	Troubleshooting - fix a problem with my device...	0.0	No	1	No	1	0	98674899-e129-492a-8d86-2c2af6024a82	46.0	13.0	13.0	10.0	/support/topic/wireless, /buy/phones/details, ...	0.0	7.0	2.0	17.5	0.0	295.0	019bab3a-e4fc-48e8-b54a-d3c241aa8465	98674899-e129-492a-8d86-2c2af6024a82	26/11/2021	38:58.3	/support/	NaN	Link_Click	2
2	GUhYhGecMg3xfNbf0mJ9j97Dybjj2Lto	019bab3a-e4fc-48e8-b54a-d3c241aa8465	7.418337e+09	11/26/21	Support	Wireless	Mobile Web	Troubleshooting - fix a problem with my device...	0.0	No	1	No	1	0	98674899-e129-492a-8d86-2c2af6024a82	46.0	13.0	13.0	10.0	/support/topic/wireless, /buy/phones/details, ...	0.0	7.0	2.0	17.5	0.0	295.0	019bab3a-e4fc-48e8-b54a-d3c241aa8465	98674899-e129-492a-8d86-2c2af6024a82	26/11/2021	39:08.4	/support/	NaN	Link_Click	3
3	GUhYhGecMg3xfNbf0mJ9j97Dybjj2Lto	019bab3a-e4fc-48e8-b54a-d3c241aa8465	7.418337e+09	11/26/21	Support	Wireless	Mobile Web	Troubleshooting - fix a problem with my device...	0.0	No	1	No	1	0	98674899-e129-492a-8d86-2c2af6024a82	46.0	13.0	13.0	10.0	/support/topic/wireless, /buy/phones/details, ...	0.0	7.0	2.0	17.5	0.0	295.0	019bab3a-e4fc-48e8-b54a-d3c241aa8465	98674899-e129-492a-8d86-2c2af6024a82	26/11/2021	39:14.3	/support/topic/wireless	SUPPORT (Not Product-Specific)	Foresee_Feedback_Invite_System_Display	4
4	GUhYhGecMg3xfNbf0mJ9j97Dybjj2Lto	019bab3a-e4fc-48e8-b54a-d3c241aa8465	7.418337e+09	11/26/21	Support	Wireless	Mobile Web	Troubleshooting - fix a problem with my device...	0.0	No	1	No	1	0	98674899-e129-492a-8d86-2c2af6024a82	46.0	13.0	13.0	10.0	/support/topic/wireless, /buy/phones/details, ...	0.0	7.0	2.0	17.5	0.0	295.0	019bab3a-e4fc-48e8-b54a-d3c241aa8465	98674899-e129-492a-8d86-2c2af6024a82	26/11/2021	39:21.9	/support/topic/wireless	SUPPORT (Not Product-Specific)	Link_Click	5
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
6519	gQcYgcARZAwQB1FlUYcwxw4C	4f9bc5f4-b536-440a-aed5-60c476f0219b	7.723804e+09	2/3/22	Support	Other services from AT&T (Home phone, DSL, etc.)	Desktop	Troubleshooting - fix a problem with my device...	100.0	No	4	No	7	0	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	49.0	10.0	17.0	11.0	/, /acctmgmt/billandpay, /support/, /support/t...	0.0	2.0	4.0	18.5	0.0	861.0	4f9bc5f4-b536-440a-aed5-60c476f0219b	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	03/02/2022	37:37.0	/acctmgmt/accountoverview	ONLINE CARE (Not Product-Specific)	Link_Click	12
6520	gQcYgcARZAwQB1FlUYcwxw4C	4f9bc5f4-b536-440a-aed5-60c476f0219b	7.723804e+09	2/3/22	Support	Other services from AT&T (Home phone, DSL, etc.)	Desktop	Troubleshooting - fix a problem with my device...	100.0	No	4	No	7	0	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	49.0	10.0	17.0	11.0	/, /acctmgmt/billandpay, /support/, /support/t...	0.0	2.0	4.0	18.5	0.0	861.0	4f9bc5f4-b536-440a-aed5-60c476f0219b	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	03/02/2022	37:41.0	/acctmgmt/accountoverview	ONLINE CARE (Not Product-Specific)	Link_Click	13
6521	gQcYgcARZAwQB1FlUYcwxw4C	4f9bc5f4-b536-440a-aed5-60c476f0219b	7.723804e+09	2/3/22	Support	Other services from AT&T (Home phone, DSL, etc.)	Desktop	Troubleshooting - fix a problem with my device...	100.0	No	4	No	7	0	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	49.0	10.0	17.0	11.0	/, /acctmgmt/billandpay, /support/, /support/t...	0.0	2.0	4.0	18.5	0.0	861.0	4f9bc5f4-b536-440a-aed5-60c476f0219b	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	03/02/2022	38:00.0	/acctmgmt/accountoverview	ONLINE CARE (Not Product-Specific)	Link_Click	14
6522	gQcYgcARZAwQB1FlUYcwxw4C	4f9bc5f4-b536-440a-aed5-60c476f0219b	7.723804e+09	2/3/22	Support	Other services from AT&T (Home phone, DSL, etc.)	Desktop	Troubleshooting - fix a problem with my device...	100.0	No	4	No	7	0	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	49.0	10.0	17.0	11.0	/, /acctmgmt/billandpay, /support/, /support/t...	0.0	2.0	4.0	18.5	0.0	861.0	4f9bc5f4-b536-440a-aed5-60c476f0219b	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	03/02/2022	38:02.0	/acctmgmt/billandpay	ONLINE CARE (Not Product-Specific)	Page_Load	15
6523	gQcYgcARZAwQB1FlUYcwxw4C	4f9bc5f4-b536-440a-aed5-60c476f0219b	7.723804e+09	2/3/22	Support	Other services from AT&T (Home phone, DSL, etc.)	Desktop	Troubleshooting - fix a problem with my device...	100.0	No	4	No	7	0	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	49.0	10.0	17.0	11.0	/, /acctmgmt/billandpay, /support/, /support/t...	0.0	2.0	4.0	18.5	0.0	861.0	4f9bc5f4-b536-440a-aed5-60c476f0219b	HXh0ZV8dxwVMeLBiPcjpa33OUjRUZE1mhyMv_TsoNW4	03/02/2022	38:20.0	/acctmgmt/billandpay	ONLINE CARE (Not Product-Specific)	Link_Click	16